Matrices are good objects to store connections between dimensions/entities. However, matrix computation is often time consuming and sometimes wasteful if matrix is too sparse. Also thinking about the fact the inverse of the matrix is $O^n$. I am trying to understand that why is matrix used to store information in the perceptron. Wouldn't a functional form be more compact instead of a big sparse matrix to replace a perceptron layer in the neural networks?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.