Topology Optimization of Random Memristors for Input-Aware Dynamic SNN

There is unprecedented development in machine learning, exemplified by recent large language models and world simulators, which are artificial neural networks running on digital computers. However, they still cannot parallel human brains in terms of energy efficiency and the streamlined adaptability...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Wang, Bo, Wang, Shaocong, Lin, Ning, Li, Yi, Yu, Yifei, Zhang, Yue, Yang, Jichang, Wu, Xiaoshan, He, Yangu, Wang, Songqi, Chen, Rui, Li, Guoqi, Qi, Xiaojuan, Wang, Zhongrui, Shang, Dashan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 26.07.2024
Subjects
Artificial neural networks
Brain
Computer architecture
Computer memory
Computing time
Digital computers
Energy efficiency
Hardware
Image classification
Large language models
Machine learning
Memristors
Network latency
Network topologies
Neural networks
Neuromorphic computing
Optimization
Representations
Simulators
Software
Spiking
Topology optimization
Online AccessGet full text

Cover

More Information
Summary:There is unprecedented development in machine learning, exemplified by recent large language models and world simulators, which are artificial neural networks running on digital computers. However, they still cannot parallel human brains in terms of energy efficiency and the streamlined adaptability to inputs of different difficulties, due to differences in signal representation, optimization, run-time reconfigurability, and hardware architecture. To address these fundamental challenges, we introduce pruning optimization for input-aware dynamic memristive spiking neural network (PRIME). Signal representation-wise, PRIME employs leaky integrate-and-fire neurons to emulate the brain's inherent spiking mechanism. Drawing inspiration from the brain's structural plasticity, PRIME optimizes the topology of a random memristive spiking neural network without expensive memristor conductance fine-tuning. For runtime reconfigurability, inspired by the brain's dynamic adjustment of computational depth, PRIME employs an input-aware dynamic early stop policy to minimize latency during inference, thereby boosting energy efficiency without compromising performance. Architecture-wise, PRIME leverages memristive in-memory computing, mirroring the brain and mitigating the von Neumann bottleneck. We validated our system using a 40 nm 256 Kb memristor-based in-memory computing macro on neuromorphic image classification and image inpainting. Our results demonstrate the classification accuracy and Inception Score are comparable to the software baseline, while achieving maximal 62.50-fold improvements in energy efficiency, and maximal 77.0% computational load savings. The system also exhibits robustness against stochastic synaptic noise of analogue memristors. Our software-hardware co-designed model paves the way to future brain-inspired neuromorphic computing with brain-like energy efficiency and adaptivity.
ISSN:2331-8422