NVM neuromorphic core with 64k-cell (256-by-256) phase change memory synaptic array with on-chip neuron circuits for continuous in-situ learning

Autor:	Richard C. Jordan, Masatoshi Ishii, Scott C. Lewis, Geoffrey W. Burr, Kohji Hosokawa, Sangbum Kim, Matthew J. BrightSky, Asit Kumar Ray, Christopher P. Miller, Jin-Ping Han, C. Lam, Wanki Kim, Norma E. Sosa, T. Perri
Rok vydání:	2015
Předmět:	Phase-change memory Synaptic weight medicine.anatomical_structure Neuromorphic engineering Computer science Core (graph theory) Large array medicine Electronic engineering System on a chip Neuron Electronic circuit
Zdroj:	2015 IEEE International Electron Devices Meeting (IEDM).
Popis:	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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::4fb7e228ce0fedca149cbf9734ad7d2b https://doi.org/10.1109/iedm.2015.7409716 Zobrazit plný text záznamu