Resonance for Analog Recurrent Neural Network

被引：8

作者：

Qu, Yurui ^{[1
]}

Zhou, Ming ^{[1
]}

Khoram, Erfan ^{[1
]}

Yu, Nanfang ^{[1
]}

Yu, Zongfu ^{[1
]}

机构：

[1] Univ Wisconsin, Dept Elect & Comp Engn, Madison, WI 53706 USA

来源：

ACS PHOTONICS | 2022年 / 9卷 / 05期

关键词：

resonance; temporal memory; recurrent neural networks; vowel classification; LSTM; INVERSE DESIGN;

D O I：

10.1021/acsphotonics.1c02016

中图分类号：

TB3 [工程材料学];

学科分类号：

0805 ; 080502 ;

摘要：

There is a strong interest in using physical waves for artificial neuralcomputing because of their unique advantages in fast speed and intrinsicparallelism. Resonance, as a ubiquitous feature across many wave systems, is anatural candidate for analog computing in temporal signals. We demonstrate thatresonance can be used to construct stable and scalable recurrent neural networks.By including resonators with different lifetimes, the computing system developsboth short-term and long-term memories simultaneously

引用

页码：1647 / 1654

页数：8

共 50 条

[1] Wave physics as an analog recurrent neural network
Hughes, Tyler W.
Williamson, Ian A. D.
Minkov, Momchil
Fan, Shanhui
SCIENCE ADVANCES, 2019, 5 (12):
[2] Analog Gated Recurrent Unit Neural Network for Detecting Chewing Events
Odame, Kofi
Nyamukuru, Maria
Shahghasemi, Mohsen
Bi, Shengjie
Kotz, David
IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS, 2022, 16 (06) : 1106 - 1115
[3] Metamaterial-Based Analog Recurrent Neural Network Toward Machine
Jiang, Tianxi
Li, Tianqi
Huang, Hao
Peng, Zhi-Ke
He, Qingbo
PHYSICAL REVIEW APPLIED, 2023, 19 (06)
[4] Studies on an Electronic Analog of a Recurrent Neural Network with Retrieval PhaseWeight Adaptations
Mohan, Vishwanathan
Joshi, Yashwant, V
Itagi, Anand
Gangadhar, Garipelli
JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2005, 9 (02) : 127 - 133
[5] An analog VLSI recurrent neural network learning a continuous-time trajectory
Cauwenberghs, G
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (02): : 346 - 361
[6] EXPOSURE BIAS AND STATE MATCHING IN RECURRENT NEURAL NETWORK VIRTUAL ANALOG MODELS
Peussa, Aleksi
Damskagg, Eero-Pekka
Sherson, Thomas
Mimilakis, Srylianos, I
Juvela, Lauri
Gotsopoulos, Athanasios
Valimaki, Vesa
2021 24TH INTERNATIONAL CONFERENCE ON DIGITAL AUDIO EFFECTS (DAFX), 2021, : 284 - 291
[7] Stochastic Resonance in Recurrent Neural Network with Hopfield-Type Memory
Naofumi Katada
Haruhiko Nishimura
Neural Processing Letters, 2009, 30 : 145 - 154
[8] Stochastic Resonance in Recurrent Neural Network with Hopfield-Type Memory
Katada, Naofumi
Nishimura, Haruhiko
NEURAL PROCESSING LETTERS, 2009, 30 (02) : 145 - 154
[9] Stochastic Resonance Enables BPP/log* Complexity and Universal Approximation in Analog Recurrent Neural Networks
Redd, Emmett
Younger, A. Steven
Obafemi-Ajayi, Tayo
2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
[10] GENERALIZATION IN AN ANALOG NEURAL NETWORK
STARIOLO, DA
TAMARIT, FA
PHYSICAL REVIEW A, 1992, 46 (08): : 5249 - 5252

← 1 2 3 4 5 →