[23p-E102-1~14] FS.1 Focused Session "AI Electronics"

[23p-E102-13] Physical Deep Learning with Augmented Direct Feedback Alignment and Its Optoelectronic Implementation

〇Mitsumasa Nakajima¹, Katsuma Inoue², Kenji Tanaka, Yasuo Kuniyoshi², Toshikazu Hashimoto¹, Kohei Nakajima² (1.NTT Device Technology Labs., 2.Tokyo Univ.)

Keywords:Reservoir computing, Machine learning, Neural network

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.