THANKS………for ur wonderful and helpful BLOG.
    I started learning from ur blog and UFLDL tutorial.I am not good enough in MATLAB programming..Can u please send the complete softmaxPredict.m file.

    • Eric

      Things under %%—YOUR CODE HERE—:
      M = theta * data;
      maxM = max(M, [], 1);
      M = bsxfun(@minus, M, maxM);
      M = exp(M);
      M = bsxfun(@rdivide, M, sum(M));
      M = log(M);
      [Max, pred] = max(M);

  • Manel

    please can you give me the test code , the initialisation of this function

  • louis

    I didnt get what about the bias did you inlcude de bias ??
    I think you have to inlude in your featurea a column of ones

  • adi

    What is (possible or ) the exact value for theta and lambda that I can consider…..