Mitigating effects of non-ideal synaptic device characteristics for on-chip learning
Authors:
- 1 November 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 194-199
Abstract
The cross-point array architecture with resistive synaptic devices has been proposed for on-chip implementation of weighted sum and weight update in the training process of learning algorithms. However, the non-ideal properties of the synaptic devices available today, such as the nonlinearity in weight update, limited ON/OFF range and device variations, can potentially hamper the learning accuracy. This paper focuses on the impact of these realistic properties on the learning accuracy and proposes the mitigation strategies. Unsupervised sparse coding is selected as a case study algorithm. With the calibration of the realistic synaptic behavior from the measured experimental data, our study shows that the recognition accuracy of MNIST handwriting digits degrades from ~97 % to ~65 %. To mitigate this accuracy loss, the proposed strategies include 1) the smart programming schemes for achieving linear weight update; 2) a dummy column to eliminate the off-state current; 3) the use of multiple cells for each weight element to alleviate the impact of device variations. With the improved synaptic behavior by these strategies, the accuracy increases back to ~95 %, enabling the reliable integration of realistic synaptic devices in the neuromorphic systems.Keywords
This publication has 17 references indexed in Scilit:
- Technology-design Co-optimization of Resistive Cross-point Array for Accelerating Learning Algorithms on Chip2015
- 3D synaptic architecture with ultralow sub-10 fJ energy per spike for neuromorphic computation2014
- Reduction and IR-drop compensations techniques for reliable neuromorphic computing systems2014
- Neuromorphic speech systems using advanced ReRAM-based synapse2013
- Bioinspired networks with nanoscale memristive devices that combine the unsupervised and supervised learning approaches2012
- Modeling Spiking Neural Networks on SpiNNakerComputing in Science & Engineering, 2010
- Nanoscale Memristor Device as Synapse in Neuromorphic SystemsNano Letters, 2010
- CAVIAR: A 45k Neuron, 5M Synapse, 12G Connects/s AER Hardware Sensory–Processing– Learning–Actuating System for High-Speed Visual Object Recognition and TrackingIEEE Transactions on Neural Networks, 2009
- The “independent components” of natural scenes are edge filtersVision Research, 1997
- Receptive fields, binocular interaction and functional architecture in the cat's visual cortexThe Journal of Physiology, 1962