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...
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.