Course Contents

This course is an introduction to deep learning, a branch of machine learning concerned with the development and application of modern neural networks. Deep learning algorithms extract layered high-level representations of data in a way that maximizes performance on a given task. For example, asked to recognize faces, a deep neural network may learn to represent image pixels first with edges, followed by larger shapes, then parts of the face like eyes and ears, and, finally, individual face identities. Deep learning is behind many recent advances in AI, including Siri’s speech recognition, Facebook’s tag suggestions and self-driving cars. We will cover a range of topics from basic neural networks, convolutional and recurrent network structures, deep unsupervised and reinforcement learning, and applications to problem domains like speech recognition and computer vision.

Course Synopsis

• The components of a deep neural network and how they work together • The basic types of deep neural networks (MLP, CNN, RNN, LSTM) and the type of data each is designed for • A working knowledge of vocabulary, concepts, and algorithms used in deep learning • How to build: • An end-to-end model for recognizing hand-written digit images, using a multi-class Logistic Regression and MLP (Multi-Layered Perceptron) • A CNN (Convolution Neural Network) model for improved digit recognition • An RNN (Recurrent Neural Network) model to forecast time-series data • An LSTM (Long Short Term Memory) model to process sequential text data

Course Learning Outcomes

At the conclusion of this module students should understand: • The fundamental principles, theory and approaches for learning with deep neural networks • The main variants of deep learning (such convolutional and recurrent architectures), and their typical applications • The key concepts, issues and practices when training and modeling with deep architectures; as well as have hands-on experience in using deep learning frameworks for this purpose • How to implement basic versions of some of the core deep network algorithms (such as backpropagation) • How deep learning fits within the context of other ML approaches and what learning tasks it is considered to be suited and not well suited to perform