jong un kimUsing simple instance to understand the backward propagation (Part I)John D. Carmack II (twitter @John Carmack), the legendary programmer posted an article on Facebook several months ago about how he managed…Mar 31, 2018Mar 31, 2018
jong un kimFrom Bayesian point to understand Regularized regressionWhen a model is too complex or you only have limited data dimensions compared with the model, you may face the problems of overfitting.Mar 4, 2018Mar 4, 2018
jong un kimThe difference between Softmax and Softmax-LossThe softmax loss layer computes the multinomial logistic loss of the softmax of its inputs. It’s conceptually identical to a softmax layer…Mar 1, 2018Mar 1, 2018