In this series of posts, we will learn how Artificial Neural Networks (ANN) work, starting from the basics.
Here is a nice visualisation of what’s happening in an ANN during training.
In this section, we will describe the building block of ANNs from the theory.
We expand the concepts from part 1 and describe the backpropagation algorithm.
We implement our first neural network in pure Numpy.
We add a hidden layer to our neural network.
Part 5 – Multi-class Classification (coming soon)
Let’s see how to deal with multi-class classification problems with ANNs
Part 6 – Deep Learning Libraries (coming soon)
We implement our neural network using some popular deep learning libraries such as Pytorch and Tensorflow / Keras.
Installing TensorFlow 2.0 can be troublesome. We will show a method to install it on Ubuntu 18.04 with GPU support using Docker.