深度学习
计算机科学
人工神经网络
动力系统理论
人工智能
钥匙(锁)
物理系统
前馈
最优控制
前馈神经网络
动力系统(定义)
控制(管理)
控制系统
控制工程
工程类
数学
数学优化
计算机安全
量子力学
电气工程
物理
作者
Genki Furuhata,Tomoaki Niiyama,Satoshi Sunada
出处
期刊:Physical review applied
[American Physical Society]
日期:2021-03-31
卷期号:15 (3)
被引量:1
标识
DOI:10.1103/physrevapplied.15.034092
摘要
Deep learning is the backbone of artificial-intelligence technologies, and it can be regarded as a kind of multilayer feedforward neural network. An essence of deep learning is information propagation through layers. This suggests that there is a connection between deep neural networks and dynamical systems in the sense that information propagation is explicitly modeled by the time evolution of dynamical systems. In this study, we perform pattern recognition based on the optimal control of continuous-time dynamical systems, which is suitable for physical hardware implementation. The learning is based on the adjoint method to optimally control dynamical systems, and the deep (virtual) network structures based on the time evolution of the systems are used for processing input information. As a key example, we apply the dynamics-based recognition approach to an optoelectronic delay system and demonstrate that the use of the delay system allows for image recognition and nonlinear classifications using only a few control signals. This is in contrast to conventional multilayer neural networks, which require a large number of weight parameters to be trained. The proposed approach provides insight into the mechanisms of deep network processing in the framework of an optimal control problem and presents a pathway for realizing physical computing hardware.
科研通智能强力驱动
Strongly Powered by AbleSci AI