Sangbum Kim, M. Ishii, S. Lewis, T. Perri, M. BrightSky, Wanki Kim, R. Jordan, G. Burr, N. Sosa, A. Ray, Jin P. Han, Christopher P. Miller, K. Hosokawa, C. Lam
{"title":"具有64k细胞(256 × 256)相变记忆突触阵列的NVM神经形态核心,具有片上神经元电路,用于连续原位学习","authors":"Sangbum Kim, M. Ishii, S. Lewis, T. Perri, M. BrightSky, Wanki Kim, R. Jordan, G. Burr, N. Sosa, A. Ray, Jin P. Han, Christopher P. Miller, K. Hosokawa, C. Lam","doi":"10.1109/IEDM.2015.7409716","DOIUrl":null,"url":null,"abstract":"We demonstrate a neuromorphic core with 64k-cell phase change memory (PCM) synaptic array (256 axons by 256 dendrites) with in-situ learning capability. 256 configurable on-chip neuron circuits perform leaky integrate and fire (LIF) and synaptic weight update based on spike-timing dependent plasticity (STDP). 2T-1R PCM unit cell design separates LIF and STDP learning paths, minimizing neuron circuit size. The circuit implementation of STDP learning algorithm along with 2T-1R structure enables both LIF and STDP learning to operate asynchronously and simultaneously within the array, avoiding additional complication and power consumption associated with timing schemes. We show hardware demonstration of in-situ learning with large representational capacity, enabled by large array size and analog synaptic weights of PCM cells.","PeriodicalId":336637,"journal":{"name":"2015 IEEE International Electron Devices Meeting (IEDM)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"152","resultStr":"{\"title\":\"NVM neuromorphic core with 64k-cell (256-by-256) phase change memory synaptic array with on-chip neuron circuits for continuous in-situ learning\",\"authors\":\"Sangbum Kim, M. Ishii, S. Lewis, T. Perri, M. BrightSky, Wanki Kim, R. Jordan, G. Burr, N. Sosa, A. Ray, Jin P. Han, Christopher P. Miller, K. Hosokawa, C. Lam\",\"doi\":\"10.1109/IEDM.2015.7409716\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We demonstrate a neuromorphic core with 64k-cell phase change memory (PCM) synaptic array (256 axons by 256 dendrites) with in-situ learning capability. 256 configurable on-chip neuron circuits perform leaky integrate and fire (LIF) and synaptic weight update based on spike-timing dependent plasticity (STDP). 2T-1R PCM unit cell design separates LIF and STDP learning paths, minimizing neuron circuit size. The circuit implementation of STDP learning algorithm along with 2T-1R structure enables both LIF and STDP learning to operate asynchronously and simultaneously within the array, avoiding additional complication and power consumption associated with timing schemes. We show hardware demonstration of in-situ learning with large representational capacity, enabled by large array size and analog synaptic weights of PCM cells.\",\"PeriodicalId\":336637,\"journal\":{\"name\":\"2015 IEEE International Electron Devices Meeting (IEDM)\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"152\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 IEEE International Electron Devices Meeting (IEDM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IEDM.2015.7409716\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE International Electron Devices Meeting (IEDM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IEDM.2015.7409716","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
NVM neuromorphic core with 64k-cell (256-by-256) phase change memory synaptic array with on-chip neuron circuits for continuous in-situ learning
We demonstrate a neuromorphic core with 64k-cell phase change memory (PCM) synaptic array (256 axons by 256 dendrites) with in-situ learning capability. 256 configurable on-chip neuron circuits perform leaky integrate and fire (LIF) and synaptic weight update based on spike-timing dependent plasticity (STDP). 2T-1R PCM unit cell design separates LIF and STDP learning paths, minimizing neuron circuit size. The circuit implementation of STDP learning algorithm along with 2T-1R structure enables both LIF and STDP learning to operate asynchronously and simultaneously within the array, avoiding additional complication and power consumption associated with timing schemes. We show hardware demonstration of in-situ learning with large representational capacity, enabled by large array size and analog synaptic weights of PCM cells.