all AI news
Forward-Forward Training of an Optical Neural Network. (arXiv:2305.19170v2 [cs.LG] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Neural networks (NN) have demonstrated remarkable capabilities in various
tasks, but their computation-intensive nature demands faster and more
energy-efficient hardware implementations. Optics-based platforms, using
technologies such as silicon photonics and spatial light modulators, offer
promising avenues for achieving this goal. However, training multiple trainable
layers in tandem with these physical systems poses challenges, as they are
difficult to fully characterize and describe with differentiable functions,
hindering the use of error backpropagation algorithm. The recently introduced
Forward-Forward Algorithm (FFA) eliminates the …
arxiv computation energy faster hardware light multiple nature network networks neural network neural networks optics photonics platforms silicon silicon photonics technologies training