How Convolutional Neural Networks Work, in Depth

This course explains convolutional neural networks in depth, using image classification to illustrate filtering, convolution, pooling, fully connected layers, gradient descent, and backpropagation. It also discusses when CNNs are appropriate for structured data such as images, audio, and text.

Syllabus

Intro
Trickier cases
ConvNets match pieces of the image
Filtering: The math behind the match
Convolution: Trying every possible match
Pooling
Rectified Linear Units (ReLUS)
Fully connected layer
Input vector
A neuron
Squash the result
Weighted sum-and-squash neuron
Receptive fields get more complex
Add an output layer
Exhaustive search
Gradient descent with curvature
Tea drinking temperature
Chaining
Backpropagation challenge: weights
Backpropagation challenge: sums
Backpropagation challenge: sigmoid
Backpropagation challenge: ReLU
Training from scratch
Customer data