Convolutional neural networks (CNNs): filters, pooling
How convolutional neural networks (CNNs) learn small filters shared across an image, count their weights, pool, and stack layers, from LeNet to AlexNet and VGG.
Part of Learning to see.
Read first
- Image convolution: filters, blur and edge detection
How image convolution slides a small filter over a grid of pixels: box and Gaussian blur, padding and output size, and Sobel edge detection.
- Neural networks and backpropagation, step by step
How a hidden layer lets a neural network bend its boundary, and how backpropagation, the chain rule run backwards, trains it on word counts.
Read next
- Momentum in SGD: why β = 0.9 speeds up training
How SGD with momentum keeps a running velocity of gradients, cancelling zigzags and mini-batch noise while speeding along steady directions.
- Semantic segmentation: a label for every pixel
How semantic segmentation labels every pixel: fully convolutional networks (FCN), transposed convolutions, checkerboards, and dilated convolutions.