Julio Pereyra
@ItsJulioPereyra
Wake-sleep learning offers an extremely interpretable complement to training for understanding how models learn new behaviors from reflecting on failures and successes.
You can see (and modify) the exact lessons a model learned and how exactly its adapting and improving through
You can see (and modify) the exact lessons a model learned and how exactly its adapting and improving through
Niko@nikogrupen · Oct 8The return of wake-sleep.
Wake-sleep algorithms were introduced by Hinton et al. in 1995 as a means of training neural networks by alternating two phases: a wake phase that learns from real data, and a sleep phase that learns from examples the network dreams up offline.
We're
Open quoted post →Wake-sleep algorithms were introduced by Hinton et al. in 1995 as a means of training neural networks by alternating two phases: a wake phase that learns from real data, and a sleep phase that learns from examples the network dreams up offline.
We're
0 5