Introduction to Deep Learning

We are starting off the course with a busy week. This week's module has two parts. In the first part, after a quick introduction to Deep Learning's exciting applications in self-driving cars, medical imaging, and robotics, we will learn about artificial neurons called perceptrons. The second part introduces the backpropagation algorithm, which trains a neural network through the chain rule.

This week focuses on optimization methods, starting with Stochastic Gradient Descent (SGD) and its parameters including learning rate, momentum, and decay. Covers advanced gradient descent methods and regularization techniques like dropout and batch normalization. Provides hands-on experience with Keras.

This module teaches convolutional neural networks for image analysis tasks, covering definitions, design parameters, operations, hyperparameter tuning, and applications. Includes a practical project on cancer detection using the PCam dataset.

This module covers recurrent neural networks (RNNs) for handling sequential data. Topics include bidirectional information flow, vanishing and exploding gradients, GRU and LSTM cells. Includes a practical NLP project on disaster tweet classification.

This module focuses on unsupervised learning in neural networks, covering autoencoders and GANs. Explores the importance of unsupervised learning in contexts where labeled data is scarce, with practical application in generating puppy images.