CNN Architectures — AlexNet

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

CNN Architectures — VGGNet

Small filters, deeper network.

Batch Normalization

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

Handwritten Digit Recognition Using Neural Network

Stochastic Gradient Descent

Cost Function?

Visualize Your Networks in Tensorboard

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

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…

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…

To Begin

Deep learning is one of the domains of machine learning, based on “Neural Networks”.

What is “Neural Network”?