Backpropagation-free training of deep physical neural networks
成果类型：
Article
署名作者：
Momeni, Ali; Rahmani, Babak; Mallejac, Matthieu; del Hougne, Philipp; Fleury, Romain
署名单位：
Swiss Federal Institutes of Technology Domain; Ecole Polytechnique Federale de Lausanne; Microsoft; Microsoft United Kingdom; Centre National de la Recherche Scientifique (CNRS); CNRS - Institute for Engineering & Systems Sciences (INSIS); Universite de Rennes
刊物名称：
SCIENCE
ISSN/ISSBN：
0036-12276
DOI：
10.1126/science.adi8474
发表日期：
2023-12-15
页码：
1297-1303
关键词：
摘要：
Recent successes in deep learning for vision and natural language processing are attributed to larger models but come with energy consumption and scalability issues. Current training of digital deep-learning models primarily relies on backpropagation that is unsuitable for physical implementation. In this work, we propose a simple deep neural network architecture augmented by a physical local learning (PhyLL) algorithm, which enables supervised and unsupervised training of deep physical neural networks without detailed knowledge of the nonlinear physical layer's properties. We trained diverse wave-based physical neural networks in vowel and image classification experiments, showcasing the universality of our approach. Our method shows advantages over other hardware-aware training schemes by improving training speed, enhancing robustness, and reducing power consumption by eliminating the need for system modeling and thus decreasing digital computation.