Experimental demonstration and tolerancing of a large-scale neural network (165,000 synapses), using phase-change memory as the synaptic weight element

Citations Over TimeTop 10% of 2014 papers

Abstract

Using 2 phase-change memory (PCM) devices per synapse, a 3-layer perceptron network with 164,885 synapses is trained on a subset (5000 examples) of the MNIST database of handwritten digits using a backpropagation variant suitable for NVM+selector crossbar arrays, obtaining a training (generalization) accuracy of 82.2% (82.9%). Using a neural network (NN) simulator matched to the experimental demonstrator, extensive tolerancing is performed with respect to NVM variability, yield, and the stochasticity, linearity and asymmetry of NVM-conductance response.

Related Papers

• → Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain(2021)26 cited
• → ST-MNIST -- The Spiking Tactile MNIST Neuromorphic Dataset(2020)3 cited
• → Multilayer Ferromagnetic Spintronic Devices forNeuromorphic Computing Applications(2024)