Online Training of Spiking Recurrent Neural Networks with Phase-Change Memory Synapses
arXiv:2108.01804
Abstract
Spiking recurrent neural networks (RNNs) are a promising tool for solving a wide variety of complex cognitive and motor tasks, due to their rich temporal dynamics and sparse processing. However training spiking RNNs on dedicated neuromorphic hardware is still an open challenge. This is due mainly to the lack of local, hardware-friendly learning mechanisms that can solve the temporal credit assignment problem and ensure stable network dynamics, even when the weight resolution is limited. These challenges are further accentuated, if one resorts to using memristive devices for in-memory computing to resolve the von-Neumann bottleneck problem, at the expense of a substantial increase in variability in both the computation and the working memory of the spiking RNNs. To address these challenges and enable online learning in memristive neuromorphic RNNs, we present a simulation framework of differential-architecture crossbar arrays based on an accurate and comprehensive Phase-Change Memory (PCM) device model. We train a spiking RNN whose weights are emulated in the presented simulation framework, using a recently proposed e-prop learning rule. Although e-prop locally approximates the ideal synaptic updates, it is difficult to implement the updates on the memristive substrate due to substantial PCM non-idealities. We compare several widely adapted weight update schemes that primarily aim to cope with these device non-idealities and demonstrate that accumulating gradients can enable online and efficient training of spiking RNN on memristive substrates.
References in corpus (16)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- WaveNet: A Generative Model for Raw Audio
- Language Models are Few-Shot Learners
- Training and Operation of an Integrated Neuromorphic Network Based on Metal-Oxide Memristors
- Memory and information processing in neuromorphic systems
- Dota 2 with Large Scale Deep Reinforcement Learning
- Neuromorphic computing with multi-memristive synapses
- Supervised Learning in Spiking Neural Networks with FORCE Training
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
- A recipe for creating ideal hybrid memristive-CMOS neuromorphic computing systems
- A neuromorphic systems approach to in-memory computing with non-ideal memristive devices: From mitigation to exploitation
- Rounding Methods for Neural Networks with Low Resolution Synaptic Weights
- A differential memristive synapse circuit for on-line learning in neuromorphic computing systems
- A Biologically Plausible Learning Rule for Deep Learning in the Brain
- The Geometry of Sign Gradient Descent