This is a great introduction.
- Neural Networks are great identifying patterns in data. As a classic example, if you wanted to predict housing prices, you could build a data set that maps features about houses (square feet, location, proximity to Caltrain, etc) onto their actual price, and then train a network to recognize the complex relationship between features and pricing. Training happens by feeding the network features, letting it make a guess about the price, and then correcting the guess (backpropagation).
- Convolutional Neural Networks work similarly, but with images. Instead of giving a CNN discrete features, you'll usually just use the pixels of the image itself. Through a series of layers, the CNN is able to build features itself (traditionally things like edges, corners) and learn patterns in image data. For example, a CNN might be trained on a dataset that maps images onto labels, and learn how to label new images on its own.
- A Neural Network Playground
- A Beginner's Guide To Understanding Convolutional Neural Networks
- Capsule Networks (CapsNets) – Tutorial
- Chris Olah explains neural nets
- How I Shipped a Neural Network on iOS with CoreML, PyTorch, and React Native - Detailed and awesome article.
- Generative Adversarial Networks (GANs) in 50 lines of code (PyTorch)
- Neural Networks, Types, and Functional Programming
- Recurrent Neural Networks lecture by Yoshua Bengio
- Practical Advice for Building Deep Neural Networks
- Differentiable Architecture Search - Code for DARTS: Differentiable Architecture Search paper.