Open levithomason opened 9 years ago
Momentum will improve learning. Save the previous weight value before updating it as it will be used in the momentum calcuation on the next learning cycle.
https://youtu.be/IruMm7mPDdM?t=12m32s
RProp proves orders of magnitude more efficient at navigating the error surface. Pretty exciting:
https://www.youtube.com/watch?v=Cy2g9_hR-5Y
Momentum will improve learning. Save the previous weight value before updating it as it will be used in the momentum calcuation on the next learning cycle.
https://youtu.be/IruMm7mPDdM?t=12m32s