Deep Learning Tools

Chapter 1-3 Concepts unfamiliar yet tensor, pseudoinverse of A, gradient, matrix derivatives, derivatives w.r.t. a tensor, Jacobian matrix, Hessian matrix, Shannon entropy of a random variable, Ku...

Python Part The input of math libarary should be real numbers, while numpy accepts vectors and matrices. So we prefer numpy. Normalizing the data will improve the performance because gradient ...

I found SHAP to be a very helpful and interesting tool, and this post is mainly my understanding of the two papers about SHAP by Scott M. Lundberg. The first paper is about general use of SHAP A Un...