CMOS Implementation of Spiking Equilibrium Propagation for Real-Time Learning
Authors:
- 13 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 283-286
Abstract
Equilibrium propagation (EqProp) and its adaptations for spiking neural networks (SNN) are presented as biologically plausible alternatives to back-propagation (BP) which describe a potential low-energy means of learning complex tasks in neuromorphic hardware. These algorithms are conducive to extremely efficient analog computing approaches, but a detailed analog circuit implementation and architectural outline have not yet been presented. Furthermore, current theoretical analog designs of EqProp have not addressed synapse circuit-level implementations capable of simultaneous sensing and weight updates for real-time learning. To this end, we have designed and simulated a circuit-level implementation of a spiking EqProp neuron and synapse in CMOS 65 nm technology capable of concurrent inference and weight updates for real-time learning.Keywords
Funding Information
- Department of Energy (DOE) (DE-SC0021335)
- National Science Foundation (NSF) (OIA-2040588)
This publication has 13 references indexed in Scilit:
- A 28-nm Convolutional Neuromorphic Processor Enabling Online Learning with Spike-Based Retinas2020
- Processing-In-Memory-Based On-Chip Learning With Spike-Time-Dependent Plasticity in 65-nm CMOSIEEE Solid-State Circuits Letters, 2020
- A Two-way SRAM Array based Accelerator for Deep Neural Network On-chip Training2020
- Equilibrium Propagation for Memristor-Based Recurrent Neural NetworksFrontiers in Neuroscience, 2020
- Capacitor-based Cross-point Array for Analog Neural Network with Record Symmetry and Linearity2018
- Analog CMOS-based resistive processing unit for deep neural network training2017
- PCMO-Based RRAM and NPN Bipolar Selector as Synapse for Energy Efficient STDPIEEE Electron Device Letters, 2017
- Equilibrium Propagation: Bridging the Gap between Energy-Based Models and BackpropagationFrontiers in Computational Neuroscience, 2017
- Endurance management for resistive Logic-In-Memory computing architectures2017
- The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]IEEE Signal Processing Magazine, 2012