This challenge is to return the WH_delta and WP_delta, given X, WH, WP, EPY using Sigmoid on the hidden layer and Softmax on the output layer. Test Cases will accumulate dWP and dWH to solve neural nets for XOR, AND, OR, and NAND.
[dPY,dWP,dHY,dWH]=Neural_Back_Propagation(X,WH,WP,EPY)
The Matlab Latex function for Back Propagation chart is in the function template.
Solution Stats
Solution Comments
Show comments
Loading...
Problem Recent Solvers4
Suggested Problems
-
5067 Solvers
-
Is my wife right? Now with even more wrong husband
1345 Solvers
-
2274 Solvers
-
Create a square matrix of multiples
499 Solvers
-
Change the sign of even index entries of the reversed vector
648 Solvers
More from this Author305
Problem Tags
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!