~/blog/tutorials/deep-learning

Convolution Neural Network

Jul 1, 20268 min read

CNN Introduction

A standard ANN with 784 inputs (28×28 image) and one 100-neuron hidden layer has 78,400 parameters. A 224×224 RGB image has 150,528 pixel values — the first hid…

Tutorial

Jul 1, 202610 min read

Human Brain vs CNN

The first CNNs were not designed from abstract principles. They were designed by looking at how the mammalian visual system processes information, then reproduc…

Tutorial

Jul 1, 20268 min read

All You Need to Know About Images

Before writing a single line of CNN code, you need to understand exactly what data a CNN receives. An image is not a picture — it is a tensor. Every pixel is a…

Tutorial

Jul 1, 20268 min read

Convolution Operation

The convolution operation is the core computation in every convolutional neural network. Every "layer" of a CNN is just sliding a small matrix (the filter) acro…

Tutorial

Jul 1, 20268 min read

Padding in CNN

Every convolution layer without padding shrinks the spatial dimensions. A 5×5 input with a 3×3 kernel becomes 3×3. Apply another 3×3 conv to the 3×3 output — it…