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 ...

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 ...

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.

“There is a lot of data for a coach to look at for high-level advice, while letting the watch operate as an AI training plan for day-to-day workouts,” he says.