Weights of a DNN are optimized from a random init towards an optimum value minimizing the loss. Only this final state of the weights is typically kept for testing, while the wealth of information on the geometry of the weight space, accumulated over the descent is discarded. 2/
-
-
Prikaži ovu nit
-
Here, we track the trajectory of the weights during optimization using Kalman filters, allowing us to compute distributions of the weights. We can then sample an ensemble of networks for estimating model uncertainty. 3/pic.twitter.com/8vdJrjYwQY
Prikaži ovu nit
Kraj razgovora
Novi razgovor -
-
-
I love it when kalman filters and neural networks team up
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
can listen to paper here: https://youtu.be/NvEayHR-2nU . Am thinking about adding Kalman to http://CoronavirusChart.com/
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.