Lightweight Inference for Forward-Forward Training Algorithm

arXiv:2404.05241v1 Announce Type: new
Abstract: The human brain performs tasks with an outstanding energy-efficiency, i.e., with approximately 20 Watts. The state-of-the-art Artificial/Deep Neural Networks (ANN/DNN), on the other hand, have recently been shown to consume massive amounts of energy. The training of these ANNs/DNNs is done almost exclusively based on the back-propagation algorithm, which is known to be biologically implausible. This has led to a new generation of forward-only techniques, including the Forward-Forward algorithm. In this paper, we propose a …

abstract algorithm ann anns art artificial arxiv brain cs.lg dnn efficiency energy human inference massive networks neural networks propagation state tasks training type