Capacitor Minimization in Analog Synapses for Efficient and Compact Binarized SNNs
Open Access
- 30 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Artificial Intelligence
- Vol. 2 (2) , 114-125
Abstract
Accelerating the immense workloads of Neural Networks (NNs) is a critical challenge, and analog computing-based approaches present a promising solution. Among these, the Integrate-and-Fire (IF) Spiking Neural Network (SNN) stands out for its potential in efficient neural computation. However, achieving high inference accuracy through precise multiply-accumulate (MAC) operations necessitates a large membrane capacitor—224 to 547 times larger than the synapse array at the 14nm technology node—resulting in prohibitive area costs. Additionally, the large capacitor size introduces higher energy consumption and longer access times. Thus, a key research challenge is maintaining accuracy while mitigating the costs associated with the large membrane capacitor. In this work, we propose a HW/SW Codesign method, called CapMin, for capacitor size minimization in analog computing IF-SNNs. CapMin minimizes the capacitor size by reducing the number of spike times needed for accurate operation of the HW, based on the absolute frequency of MAC level occurrences in the SW. To increase the operation of IF-SNNs to current variation, we propose the method CapMin-V, which trades capacitor size for protection based on the reduced capacitor size found in CapMin. In our experiments, CapMin achieves more than a 14× reduction in capacitor size along with a 34% reduction in energy consumption over the state of the art, while CapMin-V achieves increased variation tolerance in the IF-SNN operation, requiring only a small increase in capacitor size.Keywords
Funding Information
- German Research Foundation (405422836 (OneMemory), 506419033 (NN-Thunder))
- Taiwan National Science and Technology Council (NSTC 111-2923-E-002-014-MY3, NSTC 112-2221-E-002-116-MY3)
This publication has 23 references indexed in Scilit:
- Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based acceleratorsNature Communications, 2023
- Analog Computing in Memory (CIM) Technique for General Matrix Multiplication (GEMM) to Support Deep Neural Network (DNN) and Cosine Similarity Search Computing using 3D AND-type NOR Flash Devices2022
- Neuromorphic Silicon Photonics and Hardware-Aware Deep Learning for High-Speed InferenceJournal of Lightwave Technology, 2022
- Binarized SNNs: Efficient and Error-Resilient Spiking Neural Networks through Binarization2021
- Robust Brain-Inspired Computing: On the Reliability of Spiking Neural Network Using Emerging Non-Volatile Synapses2021
- Timely: Pushing Data Movements And Interfaces In Pim Accelerators Towards Local And In Time Domain2020
- Regularizing Activation Distribution for Training Binarized Deep Networks2019
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- High performance UTBB FDSOI devices featuring 20nm gate length for 14nm node and beyond2013