Deep Learning#g

CNN Architectures — VGGNet

Small filters, deeper network.

CNN Architectures — AlexNet

The first deep learning paper that showed state of the art performance in…

Batch Normalization

A method that accelerates training of deep neural networks by reducing Internal Covariant Shift

Visualize Your Networks in Tensorboard

I’m implementing some prominent CNN architectures in Tensorflow, and I found that it’s hard…

Regularization

Regularization is a common way to avoid model overfitting by adding an extra term in the loss function.

we often calculate the loss by computing the errors(distances) between the ground truths and the output results(as the function shown below). This might lead to a…

Handwritten Digit Recognition Using Neural Network

Backpropagation

We use gradient descent to find the best parameter set to minimize the cost, so it is necessary to compute the gradients of the…

Stochastic Gradient Descent

Cost Function?