The ever-growing demand for further advances in artificial intelligence motivated research on unconventional computation based on analog physical devices. While such computation devices mimic brain-inspired analog information processing, learning procedures still relies on methods optimized for digital processing such as backpropagation. Here, we present physical deep learning by extending a biologically plausible training algorithm called direct feedback alignment. As the proposed method is based on random projection with arbitrary nonlinear activation, we can train a physical neural network without knowledge about the physical system. In addition, we can emulate and accelerate the computation for this training on a simple and scalable physical system. We demonstrate the proof-of-concept using a hierarchically connected optoelectronic recurrent neural network called deep reservoir computer. By constructing an FPGA-assisted optoelectronic benchtop, we confirmed the potential for accelerated computation with competitive performance on benchmarks. Our results provide practical solutions for the training and acceleration of neuromorphic computation.
@article{arxiv.2204.13991,
title = {Physical Deep Learning with Biologically Plausible Training Method},
author = {Mitsumasa Nakajima and Katsuma Inoue and Kenji Tanaka and Yasuo Kuniyoshi and Toshikazu Hashimoto and Kohei Nakajima},
journal= {arXiv preprint arXiv:2204.13991},
year = {2022}
}