News

Real-world data processing applications inoda compact, low-latency, low-power computing systems.Iine chiitiko-inotyairwa komputa kugona, inopindirana simbi-oxide-semiconductor hybrid memristive neuromorphic architecture inopa yakanakira hardware hwaro hwemabasa akadaro.Kuti tiratidze kugona kwakazara kweakadaro masisitimu, isu tinokurudzira uye nekuyedza kuratidza yakazara sensor yekugadzirisa mhinduro kune chaiyo-yepasirese chinhu mashandisirwo enzvimbo.Kudhirowa kufemerwa kubva kudura owl neuroanatomy, isu takagadzira bioinspired, inofambiswa nechiitiko chinhu localization system inosanganisa mamiriro-e-the-art piezoelectric micromechanical transducer transducer ine computational graph-based neuromorphic resistive memory.Isu tinoratidza zviyero zveyakagadzirwa sisitimu inosanganisira memory-based resistive coincidence detector, kunonoka mutsara wedunhu, uye inogoneka zvizere ultrasonic transducer.Isu tinoshandisa iyi mibairo yekuyedza kugadzirisa masimulation padanho rehurongwa.Aya mafananidziro anobva ashandiswa kuongorora kugadzirisa kweangular uye kugona kwesimba kwechinhu chenzvimbo yemodhi.Mhedzisiro yacho inoratidza kuti maitiro edu anogona kuve akati wandei maodha ehukuru ane simba rakawanda pane mamicrocontrollers anoita basa rimwe chete.
Tiri kupinda munguva yeubiquitous computing uko huwandu hwemidziyo uye masisitimu akaiswa ari kukura zvakanyanya kutibatsira muhupenyu hwedu hwezuva nezuva.Aya masisitimu anotarisirwa kuti arambe achienderera mberi, achipedza simba shoma sezvinobvira achidzidzira kududzira data yavanounganidza kubva kune akawanda masensa munguva chaiyo uye kugadzira mabhinari akabuda semugumisiro wekuronga kana kuzivikanwa mabasa.Imwe yematanho akanyanya kukosha anodiwa kuti azadzise chinangwa ichi kutora ruzivo runobatsira uye rwakaomesesa kubva kune ruzha uye kazhinji rusina kukwana ruzivo rwe data.Injiniya yechinyakare inosvika kazhinji sampuli masaini masaini painogaro uye yakakwirira mwero, ichigadzira yakakura data kunyangwe pakashaikwa zvekushandisa zvinobatsira.Pamusoro pezvo, nzira idzi dzinoshandisa maitiro akaomarara edhijitari ekugadzirisa masaini kufanogadzirisa iyo (kazhinji ine ruzha) yekuisa data.Pane kudaro, biology inopa dzimwe mhinduro dzekugadzirisa zvine ruzha data data uchishandisa simba-rinoshanda, asynchronous, inofambiswa nezviitiko (spikes)2,3.Neuromorphic computing inotora kufemerwa kubva kubiological systems kuderedza computational cost maererano nesimba uye ndangariro zvinodiwa zvichienzaniswa nemaitiro echinyakare masignal process nzira4,5,6.Munguva pfupi yapfuura, hunyanzvi hwese chinangwa chehuropi-based masisitimu anoshandisa impulse neural network (TrueNorth7, BrainScaleS8, DYNAP-SE9, Loihi10, Spinnaker11) yakaratidzwa.Aya ma processor anopa yakaderera simba, yakaderera latency mhinduro dzemuchina kudzidza uye cortical wedunhu modelling.Kuti vashandise zvizere simba ravo resimba, aya neuromorphic processors anofanirwa kuve akabatana zvakananga kune chiitiko-inotyairwa sensors12,13.Nekudaro, nhasi kune mashoma ekubata maturusi anopa zvakananga data inofambiswa nechiitiko.Mienzaniso yakatanhamara ndeye dynamic visual sensors (DVS) yekuona maapplications senge tracking uye kufamba kwekuona14,15,16,17 the silicon cochlea18 uye neuromorphic auditory sensors (NAS)19 yeauditory sign process, olfactory sensors20 uye yakawanda mienzaniso21,22 yekubata..texture sensors.
Mubepa rino, tinopa ichangoburwa chiitiko-inofambiswa neadhidhiyo system yekumisikidza inoshandiswa kune chinhu chinowanikwa munharaunda.Pano, kekutanga, tinotsanangura magumo-kusvika-kumagumo sisitimu yechinhu chinowanikwa munzvimbo inowanikwa nekubatanidza nyika-ye-the-art piezoelectric micromachined ultrasonic transducer (pMUT) ine computational graph yakavakirwa neuromorphic resistive memory (RRAM).In-memory computing architectures uchishandisa RRAM mhinduro inovimbisa yekudzikisa simba rekushandisa23,24,25,26,27,28,29.Kusagadzikana kwavo kwechisikigo-kusingade kushandiswa kwesimba rinoshanda kuchengetedza kana kugadzirisa ruzivo-yakanyatsoenderana neasynchronous, inofambiswa nechiitiko chimiro cheneuromorphic computing, zvichikonzera pedyo-pasina simba rekushandisa kana sisitimu isingaite.Piezoelectric micromachined ultrasonic transducers (pMUTs) isingadhuri, miniaturized silicon-based ultrasonic transducers inokwanisa kuita sevanotumira uye vanogamuchira30,31,32,33,34.Kuti tigadzirise masaini anogamuchirwa neakavakirwa-mukati masensa, isu takakwevera kurudziro kubva mudura rezizi neuroanatomy35,36,37.Zizi remudura reTyto alba rinozivikanwa nehunyanzvi hwaro hwekuvhima husiku nekuda kweiyo inoshanda kwazvo yekuongorora nzvimbo system.Kuti uverenge nzvimbo yemhuka, dura rezizi renzvimbo inoisa nguva yekubhururuka (ToF) apo masaisai eruzha kubva kune zvakapambwa anosvika kune imwe neimwe nzeve dzezizi kana manzwi ekugamuchira.Tichifunga chinhambwe chiri pakati penzeve, mutsauko uripo pakati pezviyero zviviri zveToF (Interaural Time Difference, ITD) inoita kuti zvikwanise kuverenga nekuongorora azimuth chinzvimbo chechinangwa.Kunyangwe masisitimu ebhayoloji asina kunyatsokodzera kugadzirisa algebraic equations, anogona kugadzirisa matambudziko enzvimbo nemazvo.Zizi rezizi retsinga rinoshandisa seti ye coincidence detector (CD) 35 neurons (kureva, neuroni dzinokwanisa kuona kuwirirana kwechinguvana pakati pezvipikisi zvinopararira zvichidzika kusvika kumagumo ekugadzirisa zvinofadza)
Tsvagiridzo yapfuura yakaratidza kuti complementary metal-oxide-semiconductor (CMOS) hardware uye RRAM-based neuromorphic hardware yakafuridzirwa neiyo yakaderera colliculus ("auditory cortex") yezizi remudura inzira inoshanda yekuverenga chinzvimbo uchishandisa ITD13, 40, 41, 42, 43, 44, 45, 46. Zvisinei, kukwanisa kwemaitiro akazara neuromorphic anobatanidza zvinyorwa zvekunzwa kune neuromorphic computational graphs hazvisati zvaratidzwa.Dambudziko guru nderekusiyana kwakasiyana kweanalog CMOS maseketi, ayo anokanganisa kurongeka kwekuonekwa kwemutambo.Munguva pfupi yapfuura, kumwe kuita kwenhamba kweiyo ITD47 fungidziro kwakaratidzwa.Mubepa rino, isu tinokurudzira kushandisa kugona kweRRAM kushandura kukosha kwemaitiro nenzira isiri-inotenderera kurwisa kusiyanisa mumaseketi eanalog.Isu takaita hurongwa hwekuyedza hunosanganisira imwe pMUT yekutapurirana membrane inoshanda pafrequency ye111.9 kHz, maviri pMUT inogamuchira membrane (sensors) inotevedzera nzeve dzezizi, uye imwe.Isu takaedza kuratidza iyo pMUT yekuona sisitimu uye RRAM-yakavakirwa ITD computational graph kuti tiedze yedu yenzvimbo sisitimu uye kuongorora ayo angular kugadzirisa.
Isu tinofananidza nzira yedu nedhijitari yekumisikidza pane microcontroller ichiita yakafanana yenzvimbo basa uchishandisa yakajairwa beamforming kana neuromorphic nzira, pamwe nemunda programmable gedhi array (FPGA) yeITD fungidziro inotsanangurwa mureferensi.47. Kuenzanisa uku kunoratidza kukwikwidzana kwemasimba ekugadzirisa kwakarongwa RRAM-based analog neuromorphic system.
Mumwe wemienzaniso inokatyamadza yeyakarurama uye inoshanda chinhu chenzvimbo system inogona kuwanikwa mudura zizizi35,37,48.Manheru uye mambakwedza, zizi remudura (Tyto Alba) rinonyanya kutsamira pakuteerera kusinganzwisisi, nekushingaira kutsvaga mhuka diki dzakadai semavole kana mbeva.Idzi nyanzvi dzekunzwa dzinogona kuisa zviratidzo zvekunzwa kubva kune zvakapambwa nekururama kunoshamisa (inenge 2 °) 35, sezvakaratidzwa mumufananidzo 1a.Mazizi mazizi anopinza nzvimbo yezvitubu zvinonzwika muazimuth (yakatwasuka) ndege kubva pamusiyano wenguva iri kuuya yekubhururuka (ITD) kubva kune inonzwika sosi kusvika kune mbiri nzeve.Iyo ITD computational mechanism yakakurudzirwa naJeffress49,50 iyo inovimba neural geometry uye inoda zvinhu zviviri zvakakosha: axon, neuron's nerve fiber ichiita semutsara wekunonoka, uye ruzhinji rwekusaona detector neurons yakarongwa kuita computational system.girafu sezvinoratidzwa mumufananidzo 1b.Inzwi rinosvika kunzeve neazimuth inotsamira nguva yekunonoka (ITD).Ruzha rwunobva rwashandurwa kuita spike pateni munzeve imwe neimwe.Maaxon enzeve dzekuruboshwe nedzekurudyi anoita semitsara yekunonoka uye inotenderera paCD neurons.Sezvineiwo, neuron imwe chete munhevedzano yemaeuroni anoenderana ndiyo inogashira yekupinda panguva (apo kunonoka kunodzima chaiko) uye ichapisa zvakanyanya (masero evavakidzani anopisawo, asi neakaderera frequency).Kumisikidza mamwe ma neurons anokodha chinzvimbo chechinangwa munzvimbo pasina kuenderera mberi nekushandura ITD kumakona.Iyi pfungwa inopfupikiswa muMufananidzo 1c: semuenzaniso, kana ruzha ruchibva kudivi rerudyi apo chiratidzo chekuisa kubva munzeve yekurudyi chinofamba nzira yakareba kupfuura nzira kubva munzeve yekuruboshwe, inobhadhara nhamba yeITDs, semuenzaniso, apo neuron 2 inopindirana.Mune mamwe mazwi, CD yega yega inopindura kune imwe ITD (inozivikanwawo sekunonoka kunonoka) nekuda kwekunonoka kweaxonal.Nokudaro, uropi hunoshandura mashoko enguva pfupi kuva mashoko enzvimbo.Humbowo hweanatomical hwemuchina uyu hwawanikwa37,51.Phase-yakiyiwa macronucleus neurons inochengetedza ruzivo rwenguva pfupi nezve ruzha runouya: sezvinoreva zita ravo, vanopisa pane mamwe masaini masaini.Coincidence detector neurons yeJeffress modhi inogona kuwanikwa mune laminar musimboti.Ivo vanogashira ruzivo kubva kune macronuclear neurons, ayo maaxon anoita semitsara yekunonoka.Kuwanda kwekunonoka kunopiwa nemutsara wekunonoka kunogona kutsanangurwa nehurefu hweaxon, pamwe chete neimwe myelination pattern inoshandura conduction velocity.Tichifemerwa neauditory system yezizi remudura, takagadzira biomimetic system yekuisa zvinhu munzvimbo.Nzeve mbiri idzi dzinomiririrwa nembiri pMUT vanogamuchira.Iyo inonzwika sosi ndiyo pMUT transmitter iri pakati pavo (Fig. 1a), uye iyo computational graph inoumbwa negridi yeRRAM-based CD circuits (Fig. 1b, green), kutamba basa reCD neurons iyo inopinza inononoka.kuburikidza nedunhu, mitsara yekunonoka (yebhuruu) inoita semaaxon mumubatanidzwa webhaibheri.Iyo yakarongwa yekunzwa sisitimu inosiyana mukushanda frequency kubva kune iyo zizi, iro redhisheni system inoshanda mu 1-8 kHz renji, asi pMUT masensa anoshanda angangoita 117 kHz anoshandiswa mubasa iri.Kusarudzwa kweiyo ultrasonic transducer inotariswa zvinoenderana nehunyanzvi uye optimization maitiro.Chekutanga, kudzikisira bandwidth yekugamuchira kune imwechete frequency inovandudza kuyerwa kwechiyero uye inorerutsa nhanho yekumashure-kugadzirisa.Mukuwedzera, kushanda mu ultrasound kune mukana wekuti mapurusi akabudiswa haanzwike, saka usavhiringidza vanhu, sezvo maitiro avo ekuteerera ari ~ 20-20 kHz.
zizi remudura rinogamuchira masaisai anonzwika kubva pane chiri kupfurwa, apa richifambisa mhuka.Nguva yekubhururuka (ToF) yemafungu eruzha yakasiyana kune imwe neimwe nzeve (kunze kwekunge mhuka yakananga pamberi pezizi).Mutsetse une madota unoratidza nzira iyo masaisai eruzha kuti asvike kunzeve dzezizi remudura.Mhosva inogona kunyatsoiswa munzvimbo mundege yakachinjika zvichibva pakusiyana kwehurefu pakati penzira mbiri dzeacoustic uye inopindirana interaural time musiyano (ITD) (chifananidzo chekuruboshwe chakafuridzirwa neref. 74, copyright 2002, Society for Neuroscience).Mune yedu sisitimu, iyo pMUT transmitter (yakasviba bhuruu) inogadzira masaisai eruzha anobvongodza kubva pachinangwa.Reflected ultrasound mafungu anogamuchirwa nevaviri pMUT vanogamuchira (chiedza chegirini) uye chinogadziriswa neuromorphic processor (kurudyi).b An ITD (Jeffress) computational modhi inotsanangura manzwi anopinda munzeve dzezizi remudura anotanga kukodherwa semapikisi akakiyiwa munucleus hombe (NM) uyezve kushandisa geometrically yakarongwa gidhi yeanoenderana detector neurons mu lamellar nucleus.Kugadzira (Netherlands) (kuruboshwe).Mufananidzo weiyo neuroITD computational graph inosanganisa mitsara yekunonoka uye coincidence detector neurons, zizi biosensor system inogona kuenzanisirwa uchishandisa RRAM-based neuromorphic circuits (kurudyi).c Schematic yemuchina mukuru weJeffress, nekuda kwemutsauko muToF, nzeve mbiri idzi dzinogashira ruzha panguva dzakasiyana uye dzinotumira maaxon kubva kumagumo ese kuenda kune detector.Iwo maaxoni chikamu chenhevedzano yema coincidence detector (CD) neurons, imwe neimwe inopindura inosarudza kune yakasimba-yakabatana-yakabatana mapindiro.Nekuda kweizvozvo, maCD chete ayo anopinza anosvika aine diki nguva musiyano anonakidzwa zvakanyanya (ITD inobhadharwa chaizvo).Iyo CD inozoisa encode yechinangwa cheangular chinzvimbo.
Piezoelectric micromechanical ultrasonic transducers vari scalable ultrasonic transducers iyo inogona kubatanidzwa ne advanced CMOS tekinoroji31,32,33,52 uye ine yakaderera yekutanga voltage uye mashandisiro emagetsi pane echinyakare volumetric transducers53.Mubasa redu, membrane dhayamita ndeye 880 µm, uye iyo resonant frequency inogoverwa muhuwandu hwe110-117 kHz (Fig. 2a, ona Nzira dzeruzivo).Mubatch yezvishandiso gumi zvekuyedza, avhareji yemhando yepamusoro yaive ye50 (ref. 31).Iyo tekinoroji yasvika mukukura kwemaindasitiri uye haina bioinspired per se.Kubatanidza ruzivo kubva kumafirimu akasiyana-siyana epMUT inzira inozivikanwa, uye ruzivo rwemakona runogona kuwanikwa kubva kupMUTs uchishandisa, semuenzaniso, mabeamforming maitiro31,54.Nekudaro, iyo chiratidzo chekugadzirisa chinodiwa kubvisa ruzivo rwemakona haina kukodzera kuyerwa kwesimba rakaderera.Iyo yakarongwa sisitimu inosanganisa iyo neuromorphic data preprocessing wedunhu pMUT ine RRAM-based neuromorphic computing graph yakafemerwa neJeffress modhi (Mufananidzo 2c), ichipa imwe nzira inoshanda-inoshanda uye zviwanikwa-inomanikidzirwa hardware mhinduro.Isu takaita kuyedza umo ma sensor maviri ePMUT akaiswa anosvika gumi masendimita akaparadzana kuti ashandise akasiyana maToF manzwi anogamuchirwa nemamembrane maviri ekugamuchira.Imwe pMUT ichiita semufambisi inogara pakati pevanogamuchira.Chinangwa chaive chePVC plate 12 cm yakakura, iri kure kure D pamberi pePMUT device (Fig. 2b).Anogamuchira anorekodha ruzha rwunoratidzwa kubva muchinhu uye anopindura zvakanyanya sezvinobvira panguva yekufamba kwemasaisai eruzha.Dzokorora kuedza nekushandura nzvimbo yechinhu, yakatemwa nedaro D uye kona θ.Kufemerwa ne link.55, isu tinokurudzira neuromorphic pre-processing yepMUT masaini masaini kuti ashandure mafungu anoratidzwa kuva nhongonya yekuisa neuromorphic computational graph.Iyo ToF inoenderana nepamusoro amplitude inotorwa kubva kune imwe neimwe yeaya chiteshi uye yakavharidzirwa seiyo chaiyo nguva yezvikwiriso zvemunhu.Pamusoro pemuonde.2c inoratidza kutenderera kunodiwa kusanganisa pMUT sensor ine RRAM-yakavakirwa computational graph: kune yega yega maviri pMUT anogashira, iyo mbishi chiratidzo bhendi-pass yakasefa kuti itsetseke, igadzirise, uye yobva yapfuudzwa kune inodonha musanganisi mune yekukunda maitiro.iyo ine simba chikumbaridzo (Fig. 2d) inogadzira chiitiko chekubuda (spike) uye kupfura (LIF) neuron: iyo inobuda spike nguva inokodha iyo yakaonekwa kutiza nguva.Iyo LIF chikumbaridzo chakarongedzerwa kupesana nepMUT mhinduro, nekudaro ichidzikisa pMUT kusiyanisa kubva kune mudziyo kuenda kune mudziyo.Neiyi nzira, pachinzvimbo chekuchengetedza ruzha rwese mundangariro uye nekuchigadzirisa gare gare, isu tinongogadzira peak inoenderana neToF yeizwi wave, iyo inoumba iyo yekuisa kune resistive memory computational graph.Iwo maspikes anotumirwa akananga kumitsara yekunonoka uye anofananidzwa nemamodule ekuona machisi mune neuromorphic computation graphs.Nekuti ivo vanotumirwa kumasuwo e transistors, hapana yekuwedzera amplification circuitry inodiwa (ona Supplementary Fig. 4 kuti uwane mamwe mashoko).Kuti tiongorore kurongeka kweangular kurongeka kwakapihwa nepMUT uye yakarongwa nzira yekugadzirisa chiratidzo, takayera iyo ITD (kureva, mutsauko wenguva pakati pezviitiko zvepamusoro zvinogadzirwa nevatambi vaviri) sezvo chinhambwe uye kona yechinhu chakasiyana.Kuongorora kweITD kwakabva kwashandurwa kuita makona (ona Nzira) uye yakarongwa pamusoro pechinzvimbo chechinhu: kusava nechokwadi muITD yakayerwa kwakawedzera nedaro uye kona kune chinhu (Fig. 2e, f).Dambudziko guru ndere peak-to-noise ratio (PNR) mumhinduro yePMUT.Iyo iri kure chinhu, iyo yakaderera iyo acoustic chiratidzo, nokudaro ichideredza iyo PNR (Fig. 2f, green line).Kuderera kwePNR kunotungamirira kukuwedzera kwekusava nechokwadi mukufungidzira kweITD, zvichiita kuti kuwedzerwa kwehutano hwemunharaunda (Fig. 2f, blue line).Kune chinhu chiri chinhambwe che 50 cm kubva kune chinotapurirana, iko kweangular kurongeka kwehurongwa hunenge 10 °.Uku kudzikiswa kwakaiswa nehunhu hweiyo sensor inogona kuvandudzwa.Semuenzaniso, kumanikidzwa kunotumirwa ne emitter kunogona kuwedzerwa, nekudaro kuwedzera voltage ichityaira pMUT membrane.Imwe mhinduro yekusimudza chiratidzo chinotumirwa ndeyekubatanidza ma transmitters akawanda 56. Izvi zvinogadzirisa zvichawedzera huwandu hwekutsvaga pamutengo wekuwedzera kwesimba mari.Kuwedzera kuvandudzwa kunogona kuitwa padivi rekugamuchira.Iyo pMUT inogamuchira ruzha pasi inogona kuderedzwa zvakanyanya nekuvandudza kubatana pakati pePMUT uye yekutanga nhanho amplifier, iyo parizvino inoitwa newaya yekubatanidza uye RJ45 tambo.
mufananidzo wekristaro yepMUT ine nhanhatu 880 µm membranes dzakabatanidzwa pa 1.5 mm pitch.b Dhiagiramu yekuyera kuseta.Chinangwa chiri panzvimbo yeazimuth θ uye nechekure D. Mutakuri we pMUT anogadzira chiratidzo che 117.6 kHz chinobvondoka kubva pachinangwa chosvika vaviri vanogamuchira pMUT vane nguva yakasiyana-yekubhururuka (ToF).Musiyano uyu, unotsanangurwa semusiyano wenguva yepakati-aural (ITD), inokodha chinzvimbo chechinhu uye inogona kufungidzirwa nekufungidzira mhinduro yepamusoro yemasensa maviri anogamuchira.c Schematic yepre-processing nhanho dzekushandura pMUT yakasvibira siginecha kuita spike sequences (kureva kupinza kune neuromorphic computation graph).Iyo pMUT sensors uye neuromorphic computational magirafu akagadzirwa uye akaedzwa, uye neuromorphic pre-processing yakavakirwa pasoftware simulation.d Mhinduro yepMUT membrane payakagamuchira chiratidzo uye shanduko yayo kuita spike domain.e Ongororo yenzvimbo yeangular kurongeka sekushanda kwekona yechinhu (Θ) uye chinhambwe (D) kune chakanangana nechinhu.Iyo ITD yekubvisa nzira inoda kushoma angular kugadziriswa kweinenge 4°C.f Kurongeka kweAngular (mutsara webhuruu) uye inoenderana peak-to-ruzha reshiyo (yegirini mutsetse) maringe nechinhambwe chechinhu che Θ = 0.
Resistive memory inochengetedza ruzivo mune isingaite-volatile conductive state.Nheyo yakakosha yeiyo nzira ndeyokuti kushandurwa kwezvinhu padanho reatomu kunokonzera shanduko mune yayo magetsi conductivity57.Pano isu tinoshandisa oxide-based resistive memory ine 5nm layer yehafnium dioxide yakaiswa pakati pepamusoro nepasi titanium uye titanium nitride electrodes.Iko conductivity yeRRAM madivayiri inogona kuchinjwa nekushandisa yazvino/voltage waveform iyo inogadzira kana kutyora conductive filaments yeokisijeni vacancies pakati pemagetsi.Isu takabatanidza midziyo yakadaro58 mune yakajairwa 130 nm CMOS maitiro kuti tigadzire yakagadzirwazve inogadziriswa neuromorphic reketi ichishandisa coincidence detector uye kunonoka mutsara wedunhu (Fig. 3a).Iyo isiri-inotenderera uye analog hunhu hwechishandiso, yakasanganiswa nechiitiko-inofambiswa chimiro cheiyo neuromorphic circuit, inoderedza kushandiswa kwesimba.Dunhu rine pakarepo on / off basa: rinoshanda pakarepo mushure mekushandura, richibvumira simba kuti ridzimwe zvachose kana dunhu risina basa.Zvivako zvikuru zvekuvaka zvechirongwa chakarongwa zvinoratidzwa mufig.3b.Inoumbwa neN parallel single-resistor single-transistor (1T1R) zvimiro zvinoisa masinaptic huremu kubva painotorwa huremu hwemhepo, jekiseni mune yakajairwa synapse yeanosiyanisa pair integrator (DPI) 59, uye pakupedzisira inobaiwa mu synapse nekubatanidza uye. leakage.activated (LIF) neuron 60 (ona Nzira dzeruzivo).Iwo mabheji ekupinza anoiswa kugedhi reiyo 1T1R chimiro muchimiro chekutevedzana kwevoltage pulses nehuremu pahurongwa hwemazana ema nanoseconds.Resistive memory inogona kuiswa munzvimbo yakakwirira conductive state (HCS) nekushandisa yekunze yakanaka referensi kuVtop kana Vbottom yadzika, uye kudzoreredzwa kune yakaderera conductive state (LCS) nekuisa yakanaka voltage kuVbottom kana Vtop yadzika.Ivhareji kukosha kweHCS inogona kudzorwa nekudzikamisa purogiramu yezvino (kuteerera) yeSET (ICC) negedhi-source voltage ye transistor series (Fig. 3c).Mabasa eRRAM mudunhu akapetwa kaviri: anotungamira uye anoyera mapurusi ekuisa.
Kuongorora maelectronic microscope (SEM) mufananidzo weblue HfO2 1T1R RRAM mudziyo wakabatanidzwa mu130 nm CMOS tekinoroji ine selector transistors (650 nm paupamhi) mune yegirini.b Zvivako zvekuvaka zveyakarongwa neuromorphic schema.Iyo yekupinza voltage pulses (peaks) Vin0 uye Vin1 inoshandisa yazvino Iweight, iyo inoenderana neiyo conduction inoti G0 uye G1 ye1T1R chimiro.Iyi yazvino inobaiwa muDPI synapses uye inonakidza iyo LIF neurons.RRAM G0 uye G1 yakaiswa muHCS neLCS zvakateerana.c Kushanda kwecumulative conductance density yeboka re16K RRAM madivayiri sebasa reICC ikozvino matching, iro rinonyatso kudzora mwero wekuita.d Zviyero zvedunhu mu (a) zvinoratidza kuti G1 (muLCS) inovharisa zvinopinza kubva kuVin1 (girinhi), uye zvechokwadi iyo inobuda neuron's membrane voltage inopindura chete kune yebhuruu yekupinda kubva kuVin0.RRAM inonyatso sarudza zvinongedzo mudunhu.e Kuyera kwedunhu mu (b) kuratidza maitiro eiyo conductance kukosha G0 pane membrane voltage Vmem mushure mekushandisa voltage pulse Vin0.Kunyanya kuita, kunowedzera kusimba kwemhinduro: saka, iyo RRAM mudziyo inoshandisa I / O yekubatanidza huremu.Zviyero zvakaitwa padunhu uye zvinoratidza iyo mbiri basa reRRAM, nzira uye kuyerwa kwemapurusi ekuisa.
Chekutanga, sezvo paine maviri ekutanga conduction anoti (HCS neLCS), maRRAM anogona kuvhara kana kupotsa mapurusi ekuisa kana ari muLCS kana HCS anoti, zvichiteerana.Nekuda kweizvozvo, RRAM inonyatso sarudza zvinongedzo mudunhu.Ichi ndicho chikonzero chekukwanisa kugadzirisa zvakare zvivakwa.Kuti tiratidze izvi, tichatsanangura kugadzirwa kwedunhu rakagadzirwa redunhu redunhu muFig. 3b.Iyo RRAM inoenderana neG0 yakarongerwa muHCS, uye yechipiri RRAM G1 yakarongerwa muLCS.Input pulses inoshandiswa kune zvese Vin0 neVin1.Mhedzisiro yezvikamu zviviri zvemapulisi ekuisa akaongororwa mune zvinobuda neuroni nekuunganidza neuron membrane voltage uye chiratidzo chekubuda uchishandisa oscilloscope.Kuedza kwacho kwakabudirira apo chete mudziyo weHCS (G0) wakabatanidzwa kune pulse yeNeuron kukurudzira kushushikana kwemembrane.Izvi zvinoratidzwa muMufananidzo 3d, apo chitima cheblue pulse chinokonzera kuti membrane voltage ivake pane membrane capacitor, ukuwo chitima chegirini chinoramba chichichengetedza membrane voltage.
Chechipiri chakakosha basa reRRAM ndeyekuitwa kwehuremu hwekubatanidza.Uchishandisa RRAM's analog conductance gadziriso, I / O yekubatanidza inogona kuyerwa zvinoenderana.Muchiyedzo chechipiri, chishandiso cheG0 chakarongedzerwa kune akasiyana mazinga eHCS, uye iyo yekupinza pulse yakaiswa kune iyo VIn0 yekuisa.Iyo yekupinza pulse inodhonza yazvino (Iweight) kubva pachishandiso, iyo yakaenzana neyekuitisa uye inoenderana inogona kudonha Vtop - Vbot.Iyi huremu yazvino inozoiswa muDPI synapses uye LIF inobuda neurons.Iyo membrane voltage yezvinobuda neuroni yakanyorwa uchishandisa oscilloscope uye yakaratidzwa muFig. 3d.Iyo voltage peak yeneuron membrane mukupindura kune imwechete yekupinza pulse inoenderana nemafambisirwo eresitive memory, zvichiratidza kuti RRAM inogona kushandiswa sechinhu chinorongwa chesynaptic huremu.Aya maviri ekutanga bvunzo anoratidza kuti yakatsanangurwa RRAM-yakavakirwa neuromorphic chikuva inokwanisa kuita zvinhu zvekutanga zveiyo Jeffress mechanic, kureva mutsara wekunonoka uye coincidence detector circuit.Chikuva chedunhu chinovakwa nekuturika zvidhinha zvakatevedzana padivi, sezvivharo zviri muMufananidzo 3b, uye kubatanidza magedhi avo kune yakajairika yekupinza mutsara.Isu takagadzira, takagadzira, uye takaedza neuromorphic papuratifomu inosanganisira maviri akabuda neurons anogamuchira maviri ekuisa (Fig. 4a).Dhiyagiramu yedunhu inoratidzwa muMufananidzo 4b.Iyo yepamusoro 2 × 2 RRAM matrix inobvumira pulses yekupinza kuti iendeswe kune maviri anobuda neuroni, nepo yakaderera 2 × 2 matrix inobvumira kudzokororwa kwekubatana kweviri neuroni (N0, N1).Isu tinoratidza kuti iyi puratifomu inogona kushandiswa nekunonoka mutsara kugadzirisa uye maviri akasiyana coincidence detector mabasa, sezvakaratidzwa nezviyero zvekuedza muFig. 4c-e.
Circuit diagram yakaumbwa ne two output neuron N0 neN1 inogamuchira two inputs 0 uye 1. Midziyo mina yepamusoro yearray inotsanangura synaptic connections kubva pakupinza kusvika pakubuda, uye maseru mana epasi anotsanangura hukama hunodzokororwa pakati peeuroni.Iwo mavara eRRAMs anomiririra zvishandiso zvakagadzirirwa muHCS kurudyi: zvishandiso zviri muHCS zvinobvumira kubatanidza uye zvinomiririra uremu, nepo michina iri muLCS inovhara mapurusi ekuisa uye kudzima kubatana kune zvinobuda.b Dhiagiramu yedunhu (a) ine sere RRAM modules yakasimbiswa mubhuruu.c Mitsetse yekunonoka inoumbwa nekungoshandisa masinapsesi eDPI neLIF neurons.Iyo RRAM yakasvibirira inotarwa kuitisa yakakwira zvakakwana kuti ikwanise kukonzeresa glitch pane zvakabuda mushure mekupinda kunonoka Δt.d Schematic mufananidzo wekutungamira-isinganzwe CD yekuona yenguva inoenderana nezviratidzo.Output neuron 1, N1, moto pane zvinopinda 0 uye 1 nekunonoka kupfupi.e Direction sensitive CD circuit, dunhu rinoona kana kupinza 1 kunosvika pakupinza 0 uye kunosvika mushure mekuisa 0. Kubuda kwedunhu kunomiririrwa neuron 1 (N1).
Mutsetse wekunonoka (Mufananidzo 4c) unongoshandisa maitiro ane simba eDPI synapses uye LIF neurons kubereka spike yekupinda kubva kuVin1 kusvika kuVout1 nekunonoka Tdel.Iyo chete G3 RRAM yakabatana neVin1 uye Vout1 yakarongwa muHCS, mamwe ese maRRAM akarongwa muLCS.Chishandiso cheG3 chakarongerwa 92.6 µs kuti ive nechokwadi chekuti pulse yega yega inopinza inowedzera membrane voltage yeinobuda neuron zvakakwana kuti isvike pachikumbaridzo uye kugadzira kunonoka kubuda pulse.Iko kunonoka Tdel kunotarirwa neiyo synaptic uye neural time constants.Ma coincidence detectors anoona kuitika kwemasaini anopindirana kwenguva pfupi asi akagovaniswa nzvimbo.Direction-insensitive CD inotsamira pane zvega zvega zvinoshandura kune zvakajairika kubuda neuron (Mufananidzo 4d).Iwo maviri maRRAM anobatanidza Vin0 neVin1 kuVout1, G2 uye G4 zvakateerana akarongerwa kufambisa kwakanyanya.Kusvika panguva imwe chete yezvipikisi paVin0 neVin1 kunowedzera voltage yeN1 neuron membrane pamusoro pechikumbaridzo chinodiwa kugadzira inobuda spike.Kana iwo maviri ekuisa ari kure kure nenguva, kubhadharisa pa membrane voltage yakaunganidzwa neyekutanga kupinza inogona kunge iine nguva yekuora, ichidzivirira iyo membrane inogona N1 kusvika pakukosha kwechikumbaridzo.G1 neG2 zvakarongerwa angangoita 65 µs, izvo zvinoita kuti kuvhiya kamwe chete kwekuisa hakuwedzeri membrane voltage zvakakwana kuti ikonzere kubuda.Kuona masanga pakati pezviitiko zvakagoverwa muchadenga nenguva ibasa rakakosha rinoshandiswa mumhando dzakasiyana siyana dzekunzwa senge optical kuyerera kwakavakirwa zvipingamupinyi kunzvenga uye ruzha kunobva kunzvimbo.Nekudaro, komputa kutungamira-inonzwa uye isinganzwisisike maCD chinhu chakakosha chivakwa chekuvaka anoona uye odhiyo enzvimbo masisitimu.Sezvinoratidzwa nemaitiro ezvimiro zvenguva (ona Supplementary Fig. 2), dunhu rinorongwa rinoshandisa mutsara wakakodzera wemirairo ina yezviyero zvenguva yakakura.Nokudaro, inogona kuzadzisa panguva imwe chete zvinodiwa zvemaitiro ekuona uye inzwi.Directional-sensitive CD idunhu rinonzwa kurongeka kwenzvimbo yekusvika kwemapulses: kubva kurudyi kuenda kuruboshwe uye zvichipesana.Icho chivharo chakakosha chekuvaka mune yekutanga kufamba kwekuona network yeDrosophila yekuona system, inoshandiswa kuverenga mafambiro uye kuona kudhumhana62.Kuti uwane CD-inonzwisisa CD, mapeji maviri anofanirwa kuendeswa kune maviri neuroni akasiyana (N0, N1) uye hukama hwekutungamira hunofanira kusimbiswa pakati pavo (Fig. 4e).Kana iyo yekutanga inogashirwa, HAPANA inobata nekuwedzera voltage pa membrane yayo pamusoro pechikumbaridzo kukosha uye kutumira kunze kuvhiya.Ichi chiitiko chinobuda, zvakare, chinopisa N1 nekuda kweiyo nzira yekubatanidza yakasimbiswa mune yegirini.Kana chiitiko chekupinza Vin1 ikasvika uye inopa simba N1 uku membrane yayo ichiri yakakwira, N1 inogadzira chiitiko chinobuda chinoratidza kuti mutambo wawanikwa pakati pezviviri izvi.Directional connections inobvumira N1 kuti ibudise zvinobuda chete kana 1 ikauya mushure mekuisa 0. G0, G3, uye G7 zvakarongerwa ku73.5 µS, 67.3 µS, uye 40.2 µS, zvichiteerana, kuve nechokwadi chekuti spike imwe chete pakuisa Vin0 inonoke. inobuda spike, nepo N1's membrane inogona kungosvika pachikumbaridzo kana zvese zvinoputika zvinoputika zvasvika mukuwirirana..
Kusiyana ndiko kunokonzera kusakwana mumuenzaniso neuromorphic systems63,64,65.Izvi zvinotungamira kune heterogeneous maitiro eeurons uye synapses.Mienzaniso yezvakaipira zvakadaro inosanganisira 30% (kureva kutsauswa kwakajairwa) kusiyanisa mukuwana yekupinda, nguva isingachinji, uye nguva yekuramba, kungotaura zvishoma (ona Nzira).Dambudziko iri rinotonyanya kutaurwa kana akawanda neural circuits akabatana pamwechete, senge CD inorerekera-inonzwa inoumbwa nemaneuron maviri.Kuti ushande nemazvo, kuwana nekuora nguva dzemanyuroni maviri dzinofanira kunge dzakafanana sezvinobvira.Semuyenzaniso, mutsauko mukuru mukuwana yekupinda unogona kukonzera kuti neuron imwe iite zvekudarikidza kupuruzi yekupinza nepo imwe neuron isinga davire.Pamusoro pemuonde.Mufananidzo 5a unoratidza kuti neuroni dzakasarudzwa dzakasarudzwa dzinopindura zvakasiyana kune imwechete yekupinza pulse.Iyi neural musiyano yakakosha, semuenzaniso, kune basa rekutungamira-sensitive maCD.Muchirongwa chinoratidzwa mufig.5b, c, kupinza kwekuwedzera kweuron 1 kwakakwirira zvikuru kupfuura kweyeuron 0. Nokudaro, neuron 0 inoda mapeji matatu ekupinza (panzvimbo ye1) kusvika pachikumbaridzo, uye neuron 1, sezvinotarisirwa, inoda zviitiko zviviri zvekupinza.Kuita spike nguva-inotsamira biomimetic plasticity (STDP) inzira inogoneka yekudzikamisa kukanganiswa kweasina kujeka uye husimbe neural uye synaptic maseketi pane system performance43.Pano isu tinokurudzira kushandisa hunhu hwepurasitiki hwekuramba ndangariro senzira yekupesvedzera kukwidziridzwa kweneural input uye kuderedza mhedzisiro yekusiyana mumaseketi neuromorphic.Sezvinoratidzwa mufig.4e, mazinga ekuitisa ane hukama neRRAM synaptic mass akanyatso gadzirisa inoenderana neural membrane voltage mhinduro.Isu tinoshandisa iterative RRAM programming strategy.Kune yakapihwa mapindiro, maitiro ehuremu eiyo synaptic huremu anorongwazve kudzamara hunhu hwekunangwa hwedunhu hwawanikwa (ona Nzira).
chiyero chekuedza chemhinduro yezvipfumbamwe zvakasarurwa neuron dzemunhu kune imwecheteyo yekupuruzira.Mhinduro yacho inosiyana pakati pehuwandu hwevanhu, inokanganisa kuwana kwekuisa uye nguva isingachinji.b Kuyedza kuyerwa kwesimba remaneuroni pakusiyana kwemaneuron kunokanganisa kutungamira-inonzwa CD.Iwo maviri madirection-sensitive CD inobuda neuroni inopindura zvakasiyana kune yekupinza stimuli nekuda kwekusiyana kweuron-to-neuron.Neuron 0 ine yakaderera yekupinda kuwana pane neuron 1, saka zvinotora matatu ekuisa pulses (panzvimbo pe1) kugadzira inobuda spike.Sezvinotarisirwa, neuron 1 inosvika pachikumbaridzo nezviitiko zviviri zvekupinza.Kana kupinza 1 kunosvika Δt = 50 µs mushure mekunge neuron 0 moto, CD inoramba yakanyarara nokuti Δt yakakura kudarika nguva inogara neuron 1 (inenge 22 µs).c inoderedzwa ne Δt = 20 µs, kuitira kuti kupinza 1 kunowedzera apo neuron 1's kupisa ichiri yakakwirira, zvichiita kuti pave nekuonekwa panguva imwe chete yezviitiko zviviri zvekupinza.
Izvo zvinhu zviviri zvinoshandiswa muITD calculation column ndiwo mutsara wekunonoka uye inotungamira isinganzwe CD.Maseketi ese ari maviri anoda kurongeka chaiko kuti ive nechokwadi chekuisa chinhu chakanaka kuita.Mutsetse wekunonoka unofanirwa kuunza shanduro yakanonoka yepeak yekupinda (Fig. 6a), uye CD inofanira kushandiswa chete kana iyo inopinza ichiwira mukati mekutsvaga kwekutsvaga.Nokuda kwemutsara wekunonoka, zviyero zve synaptic zvekubatanidzwa kwekubatanidza (G3 muFig. 4a) zvakarongwazve kusvikira chinangwa chinononoka chawanikwa.Isa kushivirira kwakatenderedza chinangwa kunonoka kumisa chirongwa: iyo idiki kushivirira, zvakanyanya kuoma kuti ubudirire kuseta mutsara wekunonoka.Pamusoro pemuonde.Mufananidzo 6b unoratidza mhedzisiro yekunonoka mutsara wekugadzirisa maitiro: zvinogona kuonekwa kuti chirongwa chinorongwa chinogona kunyatsopa kunonoka kwese kunodiwa muchirongwa chekugadzira (kubva pa10 kusvika ku300 μs).Huwandu hwehuwandu hwekugadzirisa iterations hunokanganisa kunaka kwemaitiro ekugadzirisa: 200 iterations inogona kuderedza kukanganisa kusvika pasi pe5%.Imwe calibration iteration inoenderana neseti/reset mashandiro eRRAM cell.Iyo tuning maitiro akakosha zvakare kuvandudza iko kurongeka kweCD module nekukurumidza kuona chiitiko chepedyo.Zvakatora kudzokororwa kwegumi kuti uwane chiyero chechokwadi chakanaka (kureva, mwero wezviitiko zvakanyatsozivikanwa sezvine basa) pamusoro pe95% (mutsetse webhuruu muFigure 6c).Nekudaro, maitiro ekugadzirisa haana kukanganisa zviitiko zvakanaka zvenhema (kureva kuti, kuwanda kwezviitiko zvakaonekwa zvisirizvo sezvakakodzera).Imwe nzira inocherechedzwa mumasisitimu ezvipenyu ekukunda zvipingamupinyi zvenguva yekukurumidza kuita nzira nzira ndeyedundancy (kureva, makopi akawanda echinhu chimwe chete anoshandiswa kuita basa rakapihwa).Tichifemerwa nebiology66, takaisa akati wandei maCD maseketi mune yega CD module pakati pemitsetse miviri yekunonoka kuderedza kukanganiswa kwenhema.Sezvinoratidzwa mufig.6c (green line), kuisa zvinhu zvitatu zveCD muCD module yega yega zvinogona kuderedza chiyero chenhema chearamu kusvika pasi pe10-2.
Mhedzisiro yekusiyana kweuronal pakunonoka mutsara maseketi.b Delay line circuits inogona kuyerwa kusvika kunonoka kukuru nekugadzirisa nguva dzenguva dzeLIF neurons dzinoenderana uye DPI synapses kune zvakakosha.Kuwedzera huwandu hwekudzokororwa kweRRAM calibration process yakaita kuti zvikwanise kuvandudza zvakanyanya kurongeka kwechinangwa kunonoka: 200 iterations yakaderedza kukanganisa kusvika pasi pe5%.Imwe iteration inoenderana neSET/RESET oparesheni pane RRAM cell.Imwe neimwe CD modhi mu c Jeffress modhi inogona kuitwa uchishandisa N parallel CD zvinhu kuitira kuchinjika zvakanyanya maererano nekutadza kwehurongwa.d Yakawanda RRAM calibration iterations inowedzera yechokwadi yakanaka mwero (yebhuruu mutsara), nepo iyo yenhema yakanaka mwero yakazvimirira pahuwandu hwekudzokororwa (girinhi mutsara).Kuisa mamwe maCD zvinhu zvakafanana kunodzivirira kuonekwa kwenhema kwemaCD module.
Isu iye zvino tinoongorora kushanda uye kushandiswa kwesimba kwekupedzisira-ku-kuguma kwakabatanidzwa chinhu chekugadzirisa nzvimbo inoratidzwa muMufananidzo 2 tichishandisa zviyero zveacoustic properties yepMUT sensor, CD, uye kunonoka mutsara mitsara inoumba neuromorphic computing graph.Jeffress modhi (Fig. 1a).Kana iri neuromorphic computing graph, iyo yakawanda nhamba yeCD modules, zviri nani kugadzirisa angular, asiwo yakakwirira simba regadziriro (Fig. 7a).Chibvumirano chinogona kuwanikwa nekuenzanisa kurongeka kwezvikamu zvega (pMUT sensors, neurons, uye synaptic circuits) nekururama kwehurongwa hwose.Kugadziriswa kwemutsara wekunonoka kunogumira nenguva dzenguva dzema-synapses uye neurons, iyo muchirongwa chedu inodarika 10 µs, iyo inoenderana neangular resolution ye4 ° (ona Nzira).Mamwe manodhi epamberi ane tekinoroji yeCMOS anobvumira dhizaini yeneural uye synaptic maseketi ane yakaderera nguva isingachinjiki, zvichikonzera kurongeka kwakanyanya kwezvinhu zvekunonoka mutsara.Zvisinei, muhurongwa hwedu, kururamisa kunogumira nekukanganisa pMUT pakuenzanisa nzvimbo yeangular, kureva 10 ° (blue horizontal line muFig. 7a).Takagadzirisa nhamba yeCD modules pa40, iyo inofananidzwa nekugadzirisa kweangular inenge 4 °, kureva, kutendeseka kweangular ye graph computational (light blue horizontal line muFig. 7a).Padanho rehurongwa, izvi zvinopa sarudzo ye4 ° uye iko kurongeka kwe10 ° yezvinhu zviri 50 cm pamberi pe sensor system.Kukosha uku kunofananidzwa neuromorphic sound localization masisitimu anoshumwa mune ref.67. Kuenzanisa kwegadziriro yakarongwa nehurumende yehutano inogona kuwanikwa muSupplementary Table 1. Kuwedzera mamwe pMUTs, kuwedzera acoustic signal level, uye kuderedza ruzha rwemagetsi inzira dzinobvira dzekuwedzera kuvandudza kururamisa kwenzvimbo.) inofungidzirwa pa9.7.nz.55. Yakapiwa 40 CD units pane computational graph, iyo SPICE simulation inofungidzira simba pakushanda (kureva, chinhu chekuisa simba) kuva 21.6 nJ.Iyo neuromorphic system inobatidzwa chete kana chiitiko chekupinza chasvika, kureva kana acoustic wave yasvika chero pMUT inogamuchira uye yakadarika chikumbaridzo chekuona, zvikasadaro inoramba isingaite.Izvi zvinodzivirira kushandiswa kwesimba kusingakoshi kana pasina chiratidzo chekuisa.Tichifunga nezve kuwanda kwekuita kwenzvimbo ye100 Hz uye activation nguva ye300 µs pakushanda (yakanyanya inogoneka ITD), kushandiswa kwesimba kweiyo neuromorphic computing graph ndeye 61.7 nW.Neuromorphic pre-processing inoshandiswa kune yega pMUT inogamuchira, simba rekushandisa rehurongwa hwose rinosvika 81.6 nW.Kuti tinzwisise kushanda kwesimba kweiyo yakarongwa neuromorphic maitiro kana ichienzaniswa neyakajairwa Hardware, takaenzanisa nhamba iyi nesimba rinodiwa kuita basa rimwe chete pane yazvino low power microcontroller uchishandisa ingave neuromorphic kana yakajairwa beamforming68 Skill.Iyo neuromorphic nzira inotarisa analog-to-digital converter (ADC) nhanho, inoteverwa nebhendi-pass sefa uye envelopu yekubvisa nhanho (Teeger-Kaiser nzira).Pakupedzisira, chikumbaridzo oparesheni inoitwa kubvisa iyo ToF.Isu takasiya kuverenga kweITD kwakavakirwa paToF uye kutendeuka kune inofungidzirwa nzvimbo yemakona sezvo izvi zvichiitika kamwe pachiyero chega chega (ona Nzira).Tichifunga sampling rate ye250 kHz pamatanho ese ari maviri (pMUT vanogamuchira), gumi nemasere bhendi pass sefa mashandiro, matatu ekubvisa hamvuropu mashandiro, uye 1 pachikumbaridzo oparesheni pamuenzaniso, simba rose rekushandisa rinofungidzirwa pa245 microwatts.Izvi zvinoshandisa iyo microcontroller's low-power mode69, iyo inobatidza kana algorithms isiri kuita, iyo inoderedza kushandiswa kwesimba kusvika 10.8 µW.Iko kushandiswa kwesimba kwebeamforming chiratidzo chekugadzirisa mhinduro yakakurudzirwa mureferensi.31, ine 5 pMUT vanogamuchira uye 11 matanda zvakafanana akaparadzirwa mu azimuth ndege [-50 °, + 50 °], ari 11.71 mW (ona Methods chikamu ruzivo).Pamusoro pezvo, isu tinoshuma mashandisirwo emagetsi eFPGA47-based Time Difference Encoder (TDE) inofungidzirwa pa 1.5 mW sekutsiva iyo Jeffress modhi yenzvimbo yechinhu.Zvichienderana nefungidziro idzi, iyo yakarongwa neuromorphic nzira inoderedza kushandiswa kwesimba nemirairo mishanu yehukuru kana ichienzaniswa neiyo microcontroller ichishandisa classical beamforming matekiniki ekuita kwechinhu chenzvimbo.Kutora nzira yeuromorphic yekusaina kusaina pane yakasarudzika microcontroller inoderedza mashandisiro emagetsi neanosvika maviri maodha ehukuru.Kubudirira kwehurongwa hunotsanangurwa hunogona kutsanangurwa nekubatanidzwa kweasynchronous resistive-memory analog circuit inokwanisa kuita mu-memory calculations uye kushayikwa kweanalog-to-digital kutendeuka kunodiwa kuti uone zviratidzo.
Angular resolution (blue) uye simba rekushandisa (girini) yekushanda kwenzvimbo zvichienderana nehuwandu hwemaCD modules.Iyo yakasviba yebhuruu yakachinjika bhawa inomiririra kurongeka kweangular kwePMUT uye bhawa rebhuruu rakadzikama rinomiririra kurongeka kwemakona kweiyo neuromorphic computational graph.b Kushandiswa kwesimba kweiyo yakarongwa sisitimu uye kuenzanisa neaviri akakurukurwa ma microcontroller kuita uye kuita kwedhijitari kweTime Difference Encoder (TDE) 47 FPGA.
Kuti tideredze mashandisiro emagetsi echinangwa chenzvimbo yenzvimbo, takabata, takagadzira uye takaita inoshanda, inofambiswa nechiitiko RRAM-based neuromorphic circuit iyo inogadzirisa ruzivo rwechiratidzo chinogadzirwa neakavakirwa-mukati masensa kuti averenge nzvimbo yechinhu chakanangwa muchokwadi. nguva..Nepo nzira dzechinyakare dzekugadzirisa dzichiramba dzichiita sampuli dzakaonekwa uye kuita masvomhu kuti ubvise ruzivo runobatsira, yakarongwa neuromorphic mhinduro inoita maverengero asynchronously sezvo ruzivo runobatsira runosvika, kuwedzera simba rehurongwa hwemagetsi nemaodha mashanu ehukuru.Mukuwedzera, isu tinosimbisa kushanduka kweRRAM-based neuromorphic circuits.Kugona kweRRAM kushandura mafambiro nenzira isingaite (plasticity) inotsiva kusiyanisa kwemukati kweyekupedzisira-yakaderera simba analog DPI's synaptic uye neural circuits.Izvi zvinoita kuti iyi RRAM-yakavakirwa dunhu riite zvakasiyana uye rine simba.Chinangwa chedu hachisi chekubvisa mabasa akaomarara kana mapatani kubva kumasaini, asi kuisa zvinhu munzvimbo munguva chaiyo.Yedu sisitimu inogona zvakare kunyatso kudzvanya chiratidzo uye pakupedzisira kuitumira kune mamwe matanho ekugadzirisa kuita sarudzo dzakaoma pazvinenge zvichidikanwa.Muchirevo chekushandiswa kwenzvimbo, yedu neuromorphic preprocessing nhanho inogona kupa ruzivo nezve nzvimbo yezvinhu.Ruzivo urwu runogona kushandiswa, semuenzaniso, pakuona mafambiro kana kuzivikanwa kwechimiro.Isu tinosimbisa kukosha kwekubatanidza ultra low power sensors senge pMUTs neultra low power electronics.Kune izvi, neuromorphic nzira dzave dzakakosha sezvo dzakatitungamira kugadzira kutsva kwedunhu maitirwo eiyo biologically yakafuridzirwa computational nzira senge Jeffress modhi.Muchirevo che sensor fusion application, sisitimu yedu inogona kusanganiswa neyakasiyana-siyana-based sensors kuti iwane ruzivo rwakanyanya.Kunyangwe mazizi ari shasha pakutsvaga mhuka murima, ane maziso akanaka kwazvo uye anoita mubatanidzwa wekunzwa uye kutsvaga kwekuona asati abata mhuka70.Kana imwe neuron inonzwika ikapfuta, zizi rinogashira ruzivo rwarinoda kuti rione kuti rinotangira kupi kutsvaga kwekuona, nokudaro richinangisa pfungwa dzaro pachikamu chidiki chenzvimbo inooneka.Mubatanidzwa wekuona ma sensors (DVS kamera) uye inokurudzirwa yekuteerera sensor (yakavakirwa paPMUT) inofanirwa kuongororwa kuitira kuvandudzwa kweamangwana vanozvimirira vamiririri.
Iyo pMUT sensor iri paPCB ine maviri anogashira anenge 10 cm kureba, uye transmitter iri pakati pevanogamuchira.Mubasa iri, membrane yega yega yakamiswa bimorph chimiro chine maviri akaturikidzana epiezoelectric aluminum nitride (AlN) 800 nm gobvu akaiswa pakati pezvikamu zvitatu zvemolybdenum (Mo) 200 nm gobvu uye akaputirwa nejira 200 nm gobvu.iyo yepamusoro passivating SiN layer sezvinotsanangurwa mureferensi.71. Ma electrode emukati nekunze anoshandiswa kune pasi uye kumusoro kwepamusoro pe molybdenum, nepo pakati molybdenum electrode isingaenzaniswi uye inoshandiswa sepasi, zvichiita kuti membrane ine mapeji mana e electrode.
Ichi chivakwa chinobvumira kushandiswa kweyakajairwa membrane deformation, zvichikonzera kuvandudzwa kwekufambisa uye kugamuchira kunzwa.PMUT yakadaro inowanzo ratidza kunakidzwa kwekunzwa kwe700 nm/V seemitter, ichipa kudzvanywa kwepamusoro kwe270 Pa/V.Semunhu anogamuchira, imwe pMUT firimu inoratidza kupfupika kwedunhu kunzwisiswa kwe15 nA/Pa, iyo yakanangana neiyo piezoelectric coefficient yeAlN.Iyo tekinoroji kusiyanisa kwevoltage muAlN layer inotungamira kune shanduko mune resonant frequency, iyo inogona kubhadharwa nekushandisa DC bias kune pMUT.DC senitivity yakayerwa pa 0.5 kHz/V.Kune acoustic characterization, maikorofoni inoshandiswa pamberi pePMUT.
Kuyera echo pulse, takaisa rectangular ndiro ine nzvimbo inosvika 50 cm2 pamberi pepMUT kuratidza masaisai anonzwika.Ose ari maviri chinhambwe pakati pemahwendefa uye kona inoenderana nendege yepMUT inodzorwa uchishandisa yakakosha vabati.A Tectronix CPX400DP voltage sosi inorerekera matatu pMUT membranes, kugadzirisa resonant frequency kusvika 111.9 kHz31, nepo ma transmitters achifambiswa neTectronix AFG 3102 pulse jenareta inotaridzwa kune resonant frequency (111.9 kHz) uye 0.0 basa kutenderera.Iwo mafungu anoverengwa kubva kune mana ekubuda madoko ega ega pMUT anogashira anoshandurwa kuita voltages uchishandisa yakasarudzika yazvino uye voltage architecture, uye masaini anokonzeresa anogadziriswa neSpektrum data acquisition system.Muganho wekuona wairatidzwa nepMUT chiratidzo chekutora pasi pemamiriro akasiyana: isu takatamisa iyo reflector kune akasiyana madaro [30, 40, 50, 60, 80, 100] cm uye takashandura pMUT yekutsigira angle ([0, 20, 40] o ) Mufananidzo 2b unoratidza yenguva ITD yekuona kugadzirisa zvichienderana nenzvimbo inowirirana yeakona mumadhigirii.
Ichi chinyorwa chinoshandisa maviri akasiyana kubva pasherufu RRAM maseketi.Yekutanga ndeye 16,384 (16,000) zvishandiso (128 × 128 zvishandiso) mune 1T1R inogadziriswa ine imwe transistor uye imwe resistor.Chechipiri chip ndiyo neuromorphic platform inoratidzwa muFig. 4a.Iyo RRAM sero ine 5 nm gobvu HfO2 firimu rakaiswa muTiN/HfO2/Ti/TiN stack.Iyo RRAM stack inosanganiswa mune yekumashure-ye-mutsara (BEOL) yeiyo yakajairwa 130nm CMOS maitiro.RRAM-based neuromorphic circuits inopa dambudziko rekugadzira kune ese-analog emagetsi masisitimu umo maRRAM zvishandiso zvinogara pamwe neyakajairwa CMOS tekinoroji.Kunyanya, iyo conduction mamiriro eiyo RRAM mudziyo unofanirwa kuverengerwa uye kushandiswa sechinhu chinoshanduka cheiyo system.Kuti izvi zviitike, dunhu rakagadzirwa, rakagadzirwa uye rakaedzwa rinoverenga ikozvino kubva kune mudziyo kana pulse yekupinza inogamuchirwa uye inoshandisa iyi ikozvino kuyera mhinduro yekusiyanisa pair integrator (DPI) synapse.Dunhu iri rinoratidzwa muMufananidzo 3a, inomiririra zvivakwa zvekuvaka zve neuromorphic platform muMufananidzo 4a.Iyo yekupinza pulse inoita kuti gedhi reiyo 1T1R mudziyo, ichiita yazvino kuburikidza neRRAM inoenderana neyemuchina conductance G (Iweight = G(Vtop - Vx)).Iyo inverting yekupinda yeanoshanda amplifier (op-amp) wedunhu ine inogara DC bias voltage Vtop.Mhinduro yakashata yeop-amp ichapa Vx = Vtop nekupa yakaenzana ikozvino kubva kuM1.Iyo yazvino Iweight yakadzoserwa kubva kumudziyo inoiswa muDPI synapse.Iyo yakasimba ikozvino inokonzeresa kuwedzera depolarization, saka RRAM conduction inonyatso shandisa synaptic uremu.Iyi exponential synaptic current inobayiwa kuburikidza ne membrane capacitor ye Leaky Integration uye Excitation (LIF) neurons, iyo inosanganiswa semhepo.Kana iyo chikumbaridzo voltage ye membrane (iyo switching voltage ye inverter) yakakundwa, chikamu chinobuda cheneuron chinoitwa, chinogadzira chinobuda spike.Iyi pulse inodzoka uye inovharira iyo neuron's membrane capacitor pasi, zvichiita kuti ibude.Iyi denderedzwa inobva yawedzerwa ne pulse expander (isina kuratidzwa muFig. 3a), iyo inogadzira kubuda kwemhepo yeLIF neuron kune chinangwa chekuputira upamhi.Multiplexers zvakare akavakwa mumutsetse wega wega, achibvumira kuti voltage ishandiswe kumusoro uye kuzasi maelectrodes eiyo RRAM mudziyo.
Kuyedzwa kwemagetsi kunosanganisira kuongorora uye kurekodha maitiro ane simba emaseketi eanalogi, pamwe nekuronga uye kuverenga RRAM zvishandiso.Matanho ese ari maviri anoda maturusi akakosha, ese akabatanidzwa kune sensor board panguva imwe chete.Kuwanikwa kumidziyo yeRRAM mumaseketi euromorphic kunoitwa kubva kunze maturusi kuburikidza nemultiplexer (MUX).Iyo MUX inoparadzanisa iyo 1T1R sero kubva kune yakasara yedunhu kwairi, ichibvumira mudziyo kuti uverenge uye / kana kurongwa.Kuronga uye kuverenga maRRAM zvishandiso, Keithley 4200 SCS muchina unoshandiswa pamwe chete neArduino microcontroller: yekutanga yekwakaringana pulse chizvarwa uye ikozvino kuverenga, uye yechipiri yekukurumidza kuwana kune yega 1T1R zvinhu mundangariro array.Chekutanga kushanda kugadzira RRAM mudziyo.Masero anosarudzwa rimwe nerimwe uye simba rakanaka rinoshandiswa pakati pepamusoro uye pasi electrodes.Muchiitiko ichi, ikozvino inongogumira kune kurongeka kwemakumi e microamperes nekuda kwekugoverwa kwegedhi rinoenderana nemagetsi kune selector transistor.Iyo RRAM sero inogona kutenderera pakati peyakaderera conductive state (LCS) uye yakakwirira conductive state (HCS) uchishandisa RESET uye SET mashandiro, zvichiteerana.Kushanda kweSET kunoitwa nekuisa rectangular voltage pulse ine nguva ye1 μs uye peak voltage ye2.0-2.5 V kusvika kumusoro electrode, uye sync pulse yechimiro chakafanana ine peak voltage ye0.9-1.3 V kusvika gedhi rekusarudza transistor.Aya maitiro anobvumira modulate RRAM conduction pa20-150 µs nguva.Nokuda kweRESET, 1 µs yakafara, 3 V peak pulse inoshandiswa kune electrode yepasi (bit line) yesero apo gedhi regedhi riri pakati pe 2.5-3.0 V. Izvo zvinopinza uye zvinobuda zvemaseketi eanalogi zviratidzo zvine simba. .Nekupinza, takapindira maviri HP 8110 pulse jenareta neTektronix AFG3011 majenareta echiratidzo.Iyo yekupinza pulse ine hupamhi hwe1 µs uye kusimuka / kudonha mupendero we50 ns.Iyi mhando yekupuruzira inofungidzirwa kuve yakajairwa glitch mune analog glitch based maseketi.Kana iri chiratidzo chekubuda, chiratidzo chekubuda chakanyorwa uchishandisa Teledyne LeCroy 1 GHz oscilloscope.Iko kumhanya kwekutora kweoscilloscope kwakaratidza kuti haisi chinhu chinomisa mukuongorora uye kutora data redunhu.
Kushandisa masimba eanalogi yemagetsi kutevedzera maitiro eeurons uye synapses imhinduro inoyevedza uye inoshanda yekuvandudza kugona kwemakomputa.Kuipa kweiyi computational underlay ndeyekuti inosiyana kubva pachirongwa kuenda kuchirongwa.Isu takatsanangura kusiyanisa kwema neurons uye synaptic circuits (Supplementary Fig. 2a, b).Pakati pese kuratidzwa kwekusiyana, izvo zvine chekuita nenguva isingachinjiki uye kuwana kwekupinza zvine simba guru padanho rehurongwa.Iyo nguva yenguva yeLIF neuron uye DPI synapse inotarirwa neRC dunhu, uko kukosha kweR kunodzorwa neiyo bias voltage inoshandiswa kune gedhi re transistor (Vlk yeNeuron uye Vtau yesynapse), inotarisa leakage rate.Kupinza kwekupinda kunotsanangurwa seyepamusoro voltage inosvikwa neiyo synaptic uye neuronal membrane capacitors inokurudzirwa neinopinza pulse.Iko kupinza kwekuwana kunodzorwa neimwe bias transistor iyo inogadzirisa iyo yekuisa ikozvino.Iyo Monte Carlo simulation yakarongedzerwa paST Microelectronics '130nm maitiro akaitwa kuunganidza imwe yekuwedzera kuwana uye nguva yehuwandu hwehuwandu.Mhedzisiro yacho inounzwa muSupplementary Figure 2, uko kuwana kwekupinda uye nguva yenguva inoverengerwa sebasa reiyo bias voltage inodzora chiyero chekudonha.Micherechedzo yegirini inoverengera kutsauswa kwakajairwa kwenguva isingaperi kubva pazvinoreva.Zvose neurons uye synaptic circuits dzakakwanisa kuratidza nguva yakawanda yenguva yakawanda muhuwandu hwe10-5-10-2 s, sezvinoratidzwa muSupplementary Fig.Input amplification (Supplementary Fig. 2e, d) yeuronal uye synapse variability yaiva inenge 8% uye 3%, maererano.Kushaikwa kwakadaro kwakanyatso kunyorwa muzvinyorwa: zviyero zvakasiyana-siyana zvakaitwa pamhando yeDYNAP machipisi kuongorora kusawirirana pakati pehuwandu hweLIF63 neurons.Iyo synapses muBrainScale yakasanganiswa chiratidzo chip yakayerwa uye kusaenderana kwavo kwakaongororwa, uye maitiro ekugadzirisa akarongwa kuti aderedze maitiro e-system-level variability64.
Basa reRRAM mumaseketi euromorphic rakapetwa kaviri: tsananguro yezvivakwa (nzira yekupinza kune zvinobuda) uye kuisirwa huremu hwe synaptic.Iyo yekupedzisira pfuma inogona kushandiswa kugadzirisa dambudziko rekusiyana kweiyo modeled neuromorphic circuits.Isu takagadzira yakapfava yekuenzanisa maitiro inosanganisira reprogramming iyo RRAM mudziyo kudzamara dunhu riri kuongororwa rasangana nezvimwe zvinodiwa.Kune yakapihwa yekupinza, iyo inobuda inotariswa uye iyo RRAM inorongwazve kudzamara hunhu hwechinangwa hwawanikwa.Nguva yekumirira ye5 s yakaunzwa pakati pehurongwa hwekugadzirisa dambudziko rekuzorora kweRRAM zvichikonzera kuchinja kwekufamba kwenguva pfupi (Supplementary Information).Synaptic huremu hunogadziriswa kana kuenzaniswa maererano nezvinodiwa neuromorphic circuit iri kuenzanisirwa.Iyo calibration maitiro inopfupikiswa mune ekuwedzera algorithms [1, 2] inotarisa pane maviri akakosha maficha euromorphic mapuratifomu, mitsara yekunonoka uye kutungamira isinganzwisisi CD.Kune dunhu rine mutsara wekunonoka, iyo inotariswa maitiro ndeyekupa yakabuda pulse nekunonoka Δt.Kana iyo chaiyo yedunhu kunonoka iri pasi peiyo inotarirwa kukosha, iyo synaptic uremu hweG3 hunofanira kuderedzwa (G3 inofanira kudzoreredzwa uye yozoiswa kune yakaderera inoenderana ikozvino Icc).Sezvineiwo, kana kunonoka chaiko kwakakura kudarika kukosha kwechinangwa, kuitisa kweG3 kunofanirwa kuwedzerwa (G3 inofanira kutanga yagadziriswa uye yozoiswa kune yakakwira Icc kukosha).Iyi nzira inodzokororwa kusvikira kunonoka kunokonzerwa nedunhu kunoenderana nechinangwa chechinangwa uye kushivirira kunogadzirirwa kumisa maitiro ekugadzirisa.Kune maCD-asinganzwisisike maCD, maviri maRRAM zvishandiso, G1 uye G3, anobatanidzwa mukugadzirisa maitiro.Dunhu iri rine maviri ekuisa, Vin0 neVin1, inonokerwa nedt.Dunhu rinofanirwa kungopindura kunonoka kuri pasi peiyo inofananidzira renji [0,dtCD].Kana pasina peak yekubuda, asi iyo peak yekuisa iri padyo, ese maRRAM maturusi anofanirwa kukwidziridzwa kubatsira neuron kusvika pachikumbaridzo.Sezvineiwo, kana dunhu richipindura kunonoka kunopfuura dhairekitori reye dtCD, conductance inofanira kuderedzwa.Dzokorora maitiro kusvikira maitiro akakodzera awanikwa.Kuteerera ikozvino kunogona kugadziridzwa neyakavakwa-mukati analog wedunhu mune ref.72.73.Neiyi yakavakirwa-mukati dunhu, maitiro akadaro anogona kuitwa nguva nenguva kuyera sisitimu kana kuishandisa zvakare kune imwe application.
Isu tinoongorora mashandisirwo emagetsi eyeuromorphic chiratidzo chekugadzirisa maitiro pane yakajairwa 32-bit microcontroller68.Mukuongorora uku, isu tinofunga kushanda neseta yakafanana neiri bepa, ine imwe pMUT transmitter uye maviri pMUT anogamuchira.Iyi nzira inoshandisa bandpass sefa, inoteverwa nehamvuropu yekubvisa nhanho (Teeger-Kaiser), uye pakupedzisira kushanda kwechikumbaridzo kunoshandiswa kune chiratidzo kubvisa nguva yekubhururuka.Iko kuverenga kweITD uye kushandurwa kwayo kumakona ekuona kunosiiwa mukuongorora.Isu tinofunga nezve bhendi pass sefa yekushandisa tichishandisa 4th odha isingaperi impulse mhinduro sefa inoda 18 inoyangarara nzvimbo maoperation.Kubvisa hamvuropu kunoshandisa mamwe matatu anoyangarara mashandiro, uye yekupedzisira oparesheni inoshandiswa kuseta chikumbaridzo.Huwandu hwe 22 inoyangarara nzvimbo mashandiro anodiwa kufanogadzirisa chiratidzo.Chiratidzo chinotapurirwa ipfupi kuputika kwe111.9 kHz sine waveform inogadzirwa yega gumi ms zvichikonzera chinzvimbo chekushanda frequency ye100 Hz.Isu takashandisa sampling rate ye250 kHz kuenderana neNyquist uye 6 ms hwindo kune imwe neimwe kuyerwa kutora huwandu hwe1 mita.Ziva kuti 6 milliseconds inguva yekubhururuka kwechinhu chiri kure nemamita 1.Izvi zvinopa kushandiswa kwesimba kwe180 µW yeA/D shanduko pa 0.5 MSPS.Signal preprocessing ndeye 6.60 MIPS (mirayiridzo pasekondi), inogadzira 0.75 mW.Nekudaro, iyo microcontroller inogona kushandura kune yakaderera simba modhi 69 kana iyo algorithm isiri kushanda.Iyi modhi inopa static simba rekushandisa kwe10.8 μW uye yekumuka-nguva ye113 μs.Zvichipa wachi frequency ye84 MHz, iyo microcontroller inopedzisa mashandiro ese eiyo neuromorphic algorithm mukati me10 ms, uye algorithm inoverengera basa kutenderera kwe6.3%, nekudaro ichishandisa yakaderera simba mode.Mhedzisiro yemagetsi inoguma ndeye 244.7 μW.Ziva kuti isu tinosiya iyo ITD yakabuda kubva kuToF uye kutendeuka kune yekuona kona, nekudaro tichirerutsa mashandisiro emagetsi eiyo microcontroller.Izvi zvinopa kuwedzera kukosha kwekushanda kwesimba kwegadziriro yakarongwa.Sechimwe chimiro chekuwedzera chekuenzanisa, isu tinoongorora mashandisirwo emagetsi eiyo classical beamforming nzira dzakakurudzirwa mureferensi.31.54 kana yakaiswa mune imwecheteyo microcontroller68 pa 1.8V yekugovera voltage.Makumi mashanu akaenzana akaenzana pMUT membranes anoshandiswa kuwana data rekushongedza.Kana iri iyo yekugadzirisa pachayo, iyo beamforming nzira inoshandiswa kunonoka kuita.Zvinongosanganisira kushandisa kunonotsa kunzira dzinoenderana nemusiyano unotarisirwa munguva dzekusvika pakati penzira imwe neyereferensi.Kana masaini ari muchikamu, huwandu hwezviratidzo izvi huchava nesimba rakawanda mushure mekuchinja kwenguva.Kana vari kunze kwechikamu, kukanganisa kunoparadza kunodzikamisa simba rehuwandu hwavo.muhukama.Pamusoro pemuonde.31, sampling rate ye2 MHz inosarudzwa kuchinjisa data nenhamba yakazara yemasampuli.Imwe nzira ine mwero ndeyekuchengetedza mwero wakakomba we250 kHz uye kushandisa Finite Impulse Response (FIR) sefa kugadzira kunonoka kwechikamu.Isu tichafungidzira kuti kuomarara kweiyo beamforming algorithm kunonyanya kutariswa nekuchinja kwenguva, sezvo chiteshi chega chega chinotenderedzwa neFIR sefa ine gumi nematanhatu matapi munzira imwe neimwe.Kuti tiverenge nhamba yeMIPS inodiwa pakuita uku, tinotarisa hwindo re6ms pachiyero chekutora chiyero che 1 mita, 5 chiteshi, 11 mabheji anotungamira (range +/- 50 ° mumatanho gumi).75 zviyero pasekondi yakasundira iyo microcontroller kusvika pakukwirira kwayo kwe100 MIP.Link.68, zvichikonzera kupera kwesimba kwe11.26 mW kwese kwesimba kupera kwe11.71 mW mushure mekuwedzera mupiro weADC.
Data inotsigira zvakabuda muongororo iyi inowanika kubva kumunyori, FM, kana paine chikumbiro chine musoro.
Indiveri, G. & Sandamirskaya, Y. Kukosha kwenzvimbo uye nguva yekushandiswa kwechiratidzo muvamiririri veuromorphic: Dambudziko rekugadzira simba rakaderera, rinozvimiririra rinopindirana nenharaunda. Indiveri, G. & Sandamirskaya, Y. Kukosha kwenzvimbo uye nguva yekushandiswa kwechiratidzo muvamiririri veuromorphic: Dambudziko rekugadzira simba rakaderera, rinozvimiririra rinopindirana nenharaunda.Indiveri G. uye Sandamirskaya Y. Kukosha kwenzvimbo uye nguva yekugadzira zviratidzo mu neuromorphic agents: dambudziko rekugadzira pasi-simba rinozvimiririra rinosangana nenharaunda. Indiveri, G. & Sandamirskaya, Y. Indiveri, G. & Sandamirskaya, Y.Indiveri G. uye Sandamirskaya Y. Kukosha kwenzvimbo uye nguva yekugadzira zviratidzo mu neuromorphic agents: dambudziko rekugadzira pasi-simba rinozvimiririra rinosangana nenharaunda.IEEE Signal Processing.Journal 36, 16–28 (2019).
Thorpe, SJ Peak Nguva Yekusvika: Inoshanda Neural Network Coding Scheme. muEckmiller, R., Hartmann, G. & Hauske, G. (eds). muEckmiller, R., Hartmann, G. & Hauske, G. (eds).muEckmiller, R., Hartmann, G. uye Hauske, G. (eds.).MuEckmiller, R., Hartmann, G., uye Hauske, G. (eds.).Parallel processing mune neural system uye makomputa 91-94 (North-Holland Elsevier, 1990).
Levy, WB & Calvert, VG Kukurukurirana inoshandisa simba rakapetwa ka35 pane kuverenga mucortex yevanhu, asi zvose zvinodhura zvinodiwa kufanotaura nhamba ye synapse. Levy, WB & Calvert, VG Kukurukurirana inoshandisa simba rakapetwa ka35 pane kuverenga mucortex yevanhu, asi zvose zvinodhura zvinodiwa kufanotaura nhamba ye synapse.Levy, WB neCalvert, WG Kukurukurirana inoshandisa simba rakapetwa ka35 pane kuverenga mucortex yemunhu, asi zvose zvinodhura zvinodiwa kufanotaura nhamba ye synapses. Levy, WB & Calvert, VG Communication 消耗的能量是人类皮层计算的35 倍，但這两种成本都需要预测突触数量. Levy, WB & Calvert, VG KukurukuriranaLevy, WB neCalvert, WG Kukurukurirana inoshandisa simba rakapetwa ka35 pane kuverenga mucortex yemunhu, asi zvose zvinodhura zvinoda kufanotaura nhamba ye synapses.process.National Academy yeSainzi.sainzi.US 118, https://doi.org/10.1073/pnas.2008173118 (2021).
Dalgaty, T., Vianello, E., De Salvo, B. & Casas, J. Insect-inspired neuromorphic computing. Dalgaty, T., Vianello, E., De Salvo, B. & Casas, J. Insect-inspired neuromorphic computing.Dalgati, T., Vianello, E., DeSalvo, B. uye Casas, J. Insect-inspired neuromorphic computing.Dalgati T., Vianello E., DeSalvo B. uye Casas J. Insect-inspired neuromorphic computing.Current.Maonero.Sayenzi yezvipembenene.30, 59–66 (2018).
Roy, K., Jaiswal, A. & Panda, P. Towards spike-based machine intelligence ine neuromorphic computing. Roy, K., Jaiswal, A. & Panda, P. Towards spike-based machine intelligence ine neuromorphic computing. Roy, K., Jaiswal, A. & Panda, P. Towards Spike-Based Machine Intelligence neNeuromorphic Computing.Roy K, Jaiswal A, uye Panda P. Pulse-based artificial intelligence vachishandisa neuromorphic computing.Zvisikwa 575, 607–617 (2019).
Indiveri, G. & Liu, S.-C. Indiveri, G. & Liu, S.-C.Indiveri, G. naLiu, S.-K. Indiveri, G. & Liu, S.-C. Indiveri, G. & Liu, S.-C.Indiveri, G. naLiu, S.-K.Memory uye kugadzirisa ruzivo mune neuromorphic systems.process.IEEE 103, 1379–1397 (2015).
Akopyan F. et al.Truenorth: Dhizaini uye kit yemidziyo ye65 mW 1 miriyoni neuron inorongwa synaptic chip.IEEE kutengeserana.Kugadzirwa kwekombuta yeakabatanidzwa edunhu masisitimu.34, 1537–1557 (2015).
Schemmel, J. nevamwe.Live demo: yakadzikira pasi vhezheni yeBrainScaleS neuromorphic system pachiyero cheplate.2012 IEEE International Symposium pamusoro peMasekete neSystems (ISCAS), (IEEE ed.) 702–702 (2012).
Moradi, S., Qiao, N., Stefanini, F. & Indiveri, G. A scalable multicore architecture ane heterogeneous memory structures for dynamic neuromorphic asynchronous processors (DYNAPs). Moradi, S., Qiao, N., Stefanini, F. & Indiveri, G. A scalable multicore architecture ane heterogeneous memory structures for dynamic neuromorphic asynchronous processors (DYNAPs).Moradi S., Qiao N., Stefanini F. uye Indiviri G. A scalable multicore architecture ine heterogeneous memory structures for dynamic neuromorphic asynchronous processors (DYNAP). Moradi, S., Qiao, N., Stefanini, F. & Indiveri, G. 一种可扩展的多核架构，具有用于动态神经形态异步处理器的廆理器(DYNAP) Moradi, S., Qiao, N., Stefanini, F. & Indiveri, G. Rudzi rwekuwedzeredzwa kweakawanda-musimboti architecture, ine yakasarudzika ndangariro chimiro che dynamic neural processing (DYNAP).Moradi S., Qiao N., Stefanini F. uye Indiviri G. A scalable multicore architecture ine heterogeneous memory structures for dynamic neuromorphic asynchronous processors (DYNAP).IEEE Shanduko pane Biomedical sainzi.hurongwa hwemagetsi.12, 106–122 (2018).
Davis, M. nevamwe.Loihi: A neuromorphic multi-core processor ine yakadzikwa kudzidza.IEEE Micro 38, 82–99 (2018).
Furber, SB, Galluppi, F., Tembere, S. & Plana, LA Iyo SpiNNaker chirongwa. Furber, SB, Galluppi, F., Tembere, S. & Plana, LA Iyo SpiNNaker chirongwa.Ferber SB, Galluppi F., Temple S. uye Plana LA SpiNNaker chirongwa.Ferber SB, Galluppi F., Temple S. uye Plana LA SpiNNaker chirongwa.process.IEEE 102, 652–665 (2014).
Liu, S.-K. & Delbruck, T. Neuromorphic sensory systems. & Delbruck, T. Neuromorphic sensory systems.uye Delbrück T. Neuromorphic sensory systems. & Delbruck, T. 神经形态感觉系统. & Delbruck, T.uye Delbrück T. Neuromorphic sensory system.Current.Maonero.Neurobiology.20, 288–295 (2010).
Chope, T. et al.Neuromorphic sensory yekubatanidza kune yakasanganiswa inonzwika sosi nzvimbo uye kudzivirira kudhumhana.Muna 2019 paIEEE Musangano weBiomedical Circuits uye Systems (BioCAS), (IEEE Ed.) 1-4 (2019).
Risi, N., Aimar, A., Donati, E., Solinas, S. & Indiveri, G. A spike-based neuromorphic architecture ye stereo vision. Risi, N., Aimar, A., Donati, E., Solinas, S. & Indiveri, G. A spike-based neuromorphic architecture ye stereo vision.Risi N, Aymar A, Donati E, Solinas S, uye Indiveri G. A spike-based neuromorphic stereovision architecture. Risi, N., Aimar, A., Donati, E., Solinas, S. & Indiveri, G. 一种基于脉冲的立体视觉神经形态结构. Risi, N., Aimar, A., Donati, E., Solinas, S. & Indiveri, G.Risi N, Aimar A, Donati E, Solinas S, uye Indiveri G. Spike-based neuromorphic architecture ye stereo vision.pamberi.Neurorobotics 14, 93 (2020).
Osswald, M., Ieng, S.-H., Benosman, R. & Indiveri, G. A spiking neural network model of 3Dperception for event-based neuromorphic stereo vision systems. Osswald, M., Ieng, S.-H., Benosman, R. & Indiveri, G. A spiking neural network model of 3Dperception for event-based neuromorphic stereo vision systems.Oswald, M., Ieng, S.-H., Benosman, R., uye Indiveri, G. A 3D Pulsed Neural Network Perception Model for Event-Based Neuromorphic Stereo Vision Systems. Osswald, M., Ieng, S.-H., Benosman, R. & Indiveri, G. 基于事件的神经形态立体视觉系统的3Dperception 脉冲神经网统模。 Osswald, M., Ieng, S.-H., Benosman, R. & Indiveri, G. 3Dperception 脉冲神经网络模型.Oswald, M., Ieng, S.-H., Benosman, R., uye Indiveri, G. Spiked 3Dperception Neural Network Model for an Event-Based Neuromorphic Stereo Vision System.sainzi.Chirevo 7, 1-11 (2017).
Dalgaty, T. et al.Zvipembenene zvakafemerwa nekutanga kuona mafambiro anosanganisira resistive memory uye bursty neural network.Bionic biohybrid system.10928, 115–128 (2018).
D'Angelo, G. et al.Chiitiko-chakavakirwa eccentric kufamba kwekuona uchishandisa temporal musiyano wekodha.pamberi.Neurology.14, 451 (2020).