Introduction to artificial neural networks and deep learning. Topics include DL basics, history, and introduction to Pytorch; Perceptrons and their inspiration from neuroscience; Gradients, Autograd, designing deep linear systems; Training and testing neural networks, backpropagation, stochastic gradient descent; Applying Optimization and regularization to neural nets; Convolutional Neural Networks (ConvNets/CNNs); Recurrent Neural Networks (RNNs); and Modern Networks and their applications. Prerequisite: ASDS 5301, ASDS 5302, ASDS 5303.