Blending Optimal Control and Biologically Plausible Learning for Noise-Robust Physical Neural Networks
This work addresses the computational expense of training PNNs, enabling more practical use of physical systems for neuromorphic computing, though it is incremental as it builds on existing methods like direct feedback alignment.
The paper tackles the high training cost of physical neural networks (PNNs) by proposing a training approach that merges optimal control with biologically plausible learning, achieving robust noise-tolerant processing and significantly reducing training time, as verified numerically and experimentally in an optoelectronic delay system.
The rapidly increasing computational demands for artificial intelligence (AI) have spurred the exploration of computing principles beyond conventional digital computers. Physical neural networks (PNNs) offer efficient neuromorphic information processing by harnessing the innate computational power of physical processes; however, training their weight parameters is computationally expensive. We propose a training approach for substantially reducing this training cost. Our training approach merges an optimal control method for continuous-time dynamical systems with a biologically plausible training method--direct feedback alignment. In addition to the reduction of training time, this approach achieves robust processing even under measurement errors and noise without requiring detailed system information. The effectiveness was numerically and experimentally verified in an optoelectronic delay system. Our approach significantly extends the range of physical systems practically usable as PNNs.