Ali Momeni, Babak Rahmani, Matthieu Malléjac, Philipp del Hougne, Romain Fleury. Backpropagation-free training of deep physical neural networks. Science, 2023; DOI: 10.1126/science.adi8474 ...

EPFL researchers have developed an algorithm to train an analog neural network just as accurately as a digital one, enabling the development of more efficient alternatives to power-hungry deep ...

While CMQ solves the memory bottleneck, it shifts the burden to computation. To counter this, the researchers developed a novel training algorithm based on strong lottery ticket theory.

Abstract: “Deep neural networks (DNNs) are typically trained using the conventional stochastic gradient descent (SGD) algorithm. However, SGD performs poorly when applied to train networks on ...