Is a 4-bit synaptic weight resolution enough? - Constraints on enabling spike-timing dependent plasticity in neuromorphic hardware

Abstract

Large-scale neuromorphic hardware systems typically bear the trade-off between detail level and required chip resources. Especially when implementing spike-timing-dependent plasticity, reduction in resources leads to limitations as compared to floating point precision. By design, a natural modification that saves resources would be reducing synaptic weight resolution. In this study, we give an estimate for the impact of synaptic weight discretization on different levels, ranging from random walks of individual weights to computer simulations of spiking neural networks. The FACETS wafer-scale hardware system offers a 4-bit resolution of synaptic weights, which is shown to be sufficient within the scope of our network benchmark. Our findings indicate that increasing the resolution may not even be useful in light of further restrictions of customized mixed-signal synapses. In addition, variations due to production imperfections are investigated and shown to be uncritical in the context of the presented study. Our results represent a general framework for setting up and configuring hardware-constrained synapses. We suggest how weight discretization could be considered for other backends dedicated to large-scale simulations. Thus, our proposition of a good hardware verification practice may rise synergy effects between hardware developers and neuroscientists.

References in corpus (1)

• A Comprehensive Workflow for General-Purpose Neural Modeling with Highly Configurable Neuromorphic Hardware Systems

Cited by in corpus (18)

• Neuromorphic Silicon Photonic Networks
• Six networks on a universal neuromorphic computing substrate
• Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines
• Characterization and Compensation of Network-Level Anomalies in Mixed-Signal Neuromorphic Modeling Platforms
• Quantifying power use in silicon photonic neural networks
• Fast and Accurate Sparse Coding of Visual Stimuli with a Simple, Ultra-Low-Energy Spiking Architecture
• Prominent characteristics of recurrent neuronal networks are robust against low synaptic weight resolution
• Neuromorphic Learning towards Nano Second Precision
• Ultra-low Energy charge trap flash based synapse enabled by parasitic leakage mitigation
• Implementation of binary stochastic STDP learning using chalcogenide-based memristive devices
• Toward bio-inspired information processing with networks of nano-scale switching elements
• Phenomenological modeling of diverse and heterogeneous synaptic dynamics at natural density
• Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning
• Turn Down that Noise: Synaptic Encoding of Afferent SNR in a Single Spiking Neuron
• Artificial Retina Using A Hybrid Neural Network With Spatial Transform Capability
• Reward-based learning under hardware constraints - Using a RISC processor embedded in a neuromorphic substrate
• 2022 Roadmap on Neuromorphic Computing and Engineering
• Racing to Learn: Statistical Inference and Learning in a Single Spiking Neuron with Adaptive Kernels