This challenge is to return final WH and WP matrices, given XImgset, WH, WP, K, EPY using convolution(Ximg,K), ReLU on the hidden layer and Softmax on the output layer. Training images are LED binary matrices of digits 1:9 and 0. Sets of variants will be tested to show success beyond the training set. (Scale, Offset, Noise, zeroed node(s), intra-shifts).
Results of scaling/Offset/Noise indicate additional Training sets required with Offset and Scale. See Test Suite 1 Figure.
Would training images with Noise improve performance?
Test sets 2 thru 5 show various Pixelations of numbers and the Neural Net success rate. Just fun to look at the data.
Appears more training sets required and possibly more nodes to have high success. One translate not good.
[WP,WH]=ConvNN_Process(XImgset,K,WH,WP,EPY)
The matlab Latex code for making the CNN Processing chart included in template.
Solution Stats
Solution Comments
Show comments
Loading...
Problem Recent Solvers3
Suggested Problems
-
Create a function handle that reverses the input arguments of another function handle
157 Solvers
-
What is the distance from point P(x,y) to the line Ax + By + C = 0?
554 Solvers
-
Compute a dot product of two vectors x and y
1049 Solvers
-
mathematics , probability problem
69 Solvers
-
Getting the indices from a matrix
718 Solvers
More from this Author308
Problem Tags
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
