This workshop consists of two parts. Each part consists of a lecture and a hands-on coding exercise.
Part 1 - Introduction to Deep Learning and TensorFlow
Lecture (1h): introduces forward propagation, gradient descent and backpropagation, and simple MLPs.
Exercise (1h): introduces Keras, train a regression and a classification MLP.
Part 2 - Introduction to Convolutional Neural Networks
Lecture (1h): introduces CNNs and its layers - convolutions, pooling, activations, softmax. Covers briefly key advances in CNNs - Googlenet, ResNet, U-net, bounding boxes.
Exercise (1h): introduces Tensorflow in use together with Keras, train a simple, shallow conv-net.
Developed by Titus Tang, Data Science and AI Platform, Monash University.