Physical Deep Learning with Biologically Plausible Training Method
This work addresses the problem of training neuromorphic hardware for researchers in unconventional computing, though it appears incremental as it builds on existing biologically plausible methods.
The paper tackles the challenge of training physical neural networks without detailed knowledge of the underlying system by extending direct feedback alignment, a biologically plausible algorithm, and demonstrates competitive performance on benchmarks using an optoelectronic setup.
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.