Self-learning Machines based on Hamiltonian Echo Backpropagation

Abstract

A physical self-learning machine can be defined as a nonlinear dynamical system that can be trained on data (similar to artificial neural networks), but where the update of the internal degrees of freedom that serve as learnable parameters happens autonomously. In this way, neither external processing and feedback nor knowledge of (and control of) these internal degrees of freedom is required. We introduce a general scheme for self-learning in any time-reversible Hamiltonian system. We illustrate the training of such a self-learning machine numerically for the case of coupled nonlinear wave fields.

References in corpus (9)

• Photonics for artificial intelligence and neuromorphic computing
• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• Large-scale photonic Ising machine by spatial light modulation
• 422 Million Q Planar Integrated All-Waveguide Resonator with a 3.4 Billion Absorption Limited Q and Sub-MHz Linewidth
• Supervised learning in physical networks: From machine learning to learning machines
• A superconducting nanowire spiking element for neural networks
• Nonlinear Time-Reversal in a Wave Chaotic System
• Reservoir Computing Approach to Quantum State Measurement
• Time reversal of Bose-Einstein condensates

Cited by in corpus (9)

• Thermodynamic Computing via Autonomous Quantum Thermal Machines
• Tackling Sampling Noise in Physical Systems for Machine Learning Applications: Fundamental Limits and Eigentasks
• The Physical Effects of Learning
• All-optical nonlinear activation function based on stimulated Brillouin scattering
• Physical networks become what they learn
• A universal approximation theorem for nonlinear resistive networks
• A self-learning magnetic Hopfield neural network with intrinsic gradient descent adaption
• Noise-based Local Learning using Stochastic Magnetic Tunnel Junctions
• Harnessing intuitive local evolution rules for physical learning