←
^
→
Combining Inductive and Analytical Learning
TangentProp Search
The value of $\mu$ must be chosen carefully by the designer.
TangentProp is not robust to errors in the prior knowledge (it throws off Backpropagation).
TangentProp's is searching for different (maybe) hypothesis from simple Backpropagation. It searches on a different path.
José M. Vidal
.
23 of 32