Energy-based learning algorithms have recently gained a surge of interest due to their
compatibility with analog (post-digital) hardware. Existing algorithms include contrastive …

Coupled learning is a contrastive local learning scheme for tuning the properties of
individual elements within a network to achieve desired functionality of the system. It takes …

Learning algorithms based on backpropagation have enabled transformative technological
advances but alternatives based on local energy-based rules offer benefits in terms of …

We introduce frequency propagation, a learning algorithm for nonlinear physical networks.
In a resistive electrical circuit with variable resistors, an activation current is applied at a set …

Interacting many-body physical systems ranging from neural networks in the brain to folding
proteins to self-modifying electrical circuits can learn to perform diverse tasks. This learning …

As the size and ubiquity of artificial intelligence and computational machine learning (ML)
models grow, their energy consumption for training and use is rapidly becoming …

This work establishes that a physical system can perform statistical learning without gradient
computations, via an Agnostic Equilibrium Propagation (Aeqprop) procedure that combines …

Physical neural networks are artificial neural networks that mimic synapses and neurons
using physical systems or materials. These networks harness the distinctive characteristics …

As the size and ubiquity of artificial intelligence and computational machine learning models
grow, the energy required to train and use them is rapidly becoming economically and …

Mechanical metamaterials are often designed with particular properties for specific load‐
bearing functions. Alternatively, this study aims to create a class of active lattice …