KirchhoffNet: A Scalable Ultra Fast Analog Neural Network
Name
3676536.3676662.pdf
Size
10.66 MB
Format
Adobe PDF
Checksum (MD5)
ce79b32cc2ff35eec896e627cedcd5dc
Author(s)
Gao, Zhengqi
Sun, Fan-keng
Rohrer, Ron
Boning, Duane
Date Issued
October 9, 2024
Publisher
ACM|IEEE/ACM International Conference on Computer-Aided Design
Citation
Gao, Zhengqi, Sun, Fan-keng, Rohrer, Ron and Boning, Duane. 2024. "KirchhoffNet: A Scalable Ultra Fast Analog Neural Network."
Version
Final published version
Abstract
In this paper, we leverage a foundational principle of analog electronic circuitry, Kirchhoff's current and voltage laws, to introduce a distinctive class of neural network models termed KirchhoffNet. Essentially, KirchhoffNet is an analog circuit that can function as a neural network, utilizing its initial node voltages as the neural network input and the node voltages at a specific time point as the output. The evolution of node voltages within the specified time is dictated by learnable parameters on the edges connecting nodes. We demonstrate that KirchhoffNet is governed by a set of ordinary differential equations (ODEs), and notably, even in the absence of traditional layers (such as convolution layers), it attains state-of-the-art performances across diverse and complex machine learning tasks. Most importantly, KirchhoffNet can be potentially implemented as a low-power analog integrated circuit, leading to an appealing property --- irrespective of the number of parameters within a KirchhoffNet, its on-chip forward calculation can always be completed within a short time. This characteristic makes KirchhoffNet a promising and fundamental paradigm for implementing large-scale neural networks, opening a new avenue in analog neural networks for AI. Our source code and model checkpoints are publicly available: https://github.com/zhengqigao/kirchhoffnet.
Description
ICCAD ’24, October 27–31, 2024, New York, NY, USA
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3676536.3676662
