Blending Optimal Control and Biologically Plausible Learning for Noise-Robust Physical Neural Networks.

2025-01-07

Physical Review Letters

AI Summary

Physical neural networks (PNNs) suffer from prohibitively high training computational costs and poor robustness to measurement noise. To address these challenges, this work proposes a novel model-free training framework that synergistically integrates continuous-time optimal control with direct feedback alignment (DFA)—the first such combination in the literature. Crucially, it eliminates the need for precise physical system modeling while enabling efficient, noise-resilient weight optimization. The method substantially reduces training time and demonstrates superior stability and generalization under strong measurement noise, as validated through both numerical simulations and experiments on a photonic-electronic delay system. It consistently outperforms conventional gradient-based training approaches. This work broadens the class of physically realizable systems suitable for practical PNNs and establishes a new paradigm for robust, hardware-aware neuromorphic computing.

Technology Category

• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

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.

Problem

• Reducing training cost for physical neural networks
• Enhancing robustness against noise and errors
• Combining optimal control with biologically plausible training

Innovation

• Optimal control merges with biological learning.
• Training cost reduced in physical neural networks.
• Robust processing achieved despite noise and errors.