Desynchronous Learning in a Physics-Driven Learning Network — mentioned by RaisinLoaf69

Tue, 22 Mar 2022 17:15:32 GMT

Since we have no global processor, each edge is changing using only local information, a lot of stuff that makes sense in our network doesn't really make sense in ANNs and vice versa. For example, in our newest paper (https://arxiv.org/abs/2201.04626) we desynchronize the updates of our edges. Instead of changing the entire system all at once, we change random parts of it each training step. This doesn't really make sense to do in an ANN where you require global information for every edge update. The shape of the network is actually inspired by jamming solids (we're a soft matter lab), but is…

Paper and discussion history. A mention is not an endorsement.

Desynchronous Learning in a Physics-Driven Learning Network · HackerPapers discussions

Desynchronous Learning in a Physics-Driven Learning Network — mentioned by RaisinLoaf69