How can a computer distinguish between pictures of dogs and cats? Or learn to play great chess? We just need some inspiration from the human brain, linear algebra, and a bit of calculus.
This exploration dives into the fundamentals of artificial neural networks, from the math to the basic models to applications and more complicated models. Most importantly, you’ll gain an intuition for why these models work - not just a bunch of formulas.
To build an artificial learning algorithm, start with the human brain.
A refresher on vectors, matrices, and optimization.
The building block of many neural networks.
Stringing it all together.
Using a model's outputs to train it to do even better.
Models to capture structural information within data.
Models to process sequential data by remembering what we already know.
A look into stochastic ANNs, adversarial techniques, vectorization, and other advanced topics.