Neuron Deactivation Scheme for Defect-Tolerant Memristor Neural Networks
Authors:
- 8 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
As amounts of data generated from countless and ubiquitous IoT sensors are increased very sharply, memristor crossbars can be considered very suitable to edge intelligence hardware due to high energy efficiency of computing, dense and 3D integration, non-volatility, multi-state memory, CMOS compatible fabrication etc. But, due to the limits of immature fabrication technology, the memristor crossbars can have defects such as stuck-at-faults. To compensate for malfunction of neural networks caused from the fabrication-related defects, in this paper, a simple neuron deactivation scheme is reviewed and analyzed for maximizing its capability to compensate for the neural network’s performance degradation due to the memristor defects. The column deactivation scheme can be particularly useful for the edge intelligence hardware, because the defect map occupying a large amount of memory is not needed during the training. Moreover, the direct mapping from the calculated synaptic weights to the memristor crossbar can save the retraining time required for the defect-aware training scheme.Keywords
This publication has 13 references indexed in Scilit:
- Hybrid Circuit of Memristor and Complementary Metal-Oxide-Semiconductor for Defect-Tolerant Spatial Pooling with Boost-Factor AdjustmentMaterials, 2019
- Asymmetrical Training Scheme of Binary-Memristor-Crossbar-Based Neural Networks for Energy-Efficient Edge-Computing Nanoscale SystemsMicromachines, 2019
- Edge Intelligence—On the Challenging Road to a Trillion Smart Connected IoT DevicesIEEE Design & Test, 2019
- Stuck-at Fault Tolerance in RRAM Computing SystemsIEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2017
- Rescuing Memristor-based Neuromorphic Design with High Defects2017
- Deep Residual Learning for Image Recognition2016
- Technological Exploration of RRAM Crossbar Array for Matrix-Vector MultiplicationJournal of Computer Science and Technology, 2016
- Efficient training algorithms for neural networks based on memristive crossbar circuits2015
- RRAM-Based Analog Approximate ComputingIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015
- Memristor Crossbar-Based Neuromorphic Computing System: A Case StudyIEEE Transactions on Neural Networks and Learning Systems, 2014