Deep physical neural networks trained with backpropagation

Abstract Deep-learning models have become pervasive tools in science and engineering. Physics-aware training combines the scalability of backpropagation with the automatic mitigation of imperfections and noise achievable with in situ algorithms.

⚡ This is an original paraphrased summary — not copied from the abstract. Full paper available at the source link below.

• 1 However, their energy requirements now increasingly limit their scalability 1 .
• 2 Deep-learning accelerators 2–9 aim to perform deep learning energy-efficiently, usually targeting the inference phase and often by exploiting physical substrates beyond conventional electronics.
• 3 Approaches so far 10–22 have been unable to apply the backpropagation algorithm to train unconventional novel hardware in situ.

This research advances how AI systems learn, reason, and solve problems — with direct implications for automation and scientific discovery.

This summary is based on publicly available metadata and abstract. For the full research paper, visit the original source: