Does Deep Learning Still Need Backpropagation? | Synced

Now, researchers from the Victoria University of Wellington School of Engineering and Computer Science have introduced the HSIC (Hilbert-Schemidt independence criterion) bottleneck as an alternativ...

By · · 1 min read

Source: Synced | AI Technology & Industry Review

Now, researchers from the Victoria University of Wellington School of Engineering and Computer Science have introduced the HSIC (Hilbert-Schemidt independence criterion) bottleneck as an alternative to backpropagation for finding good representations.