This course introduces students to deep learning methods with application to computer vision, natural language processing, biology, and more. Students will gain foundational knowledge of deep learning algorithms, understand how to build neural networks in TensorFlow, and learn to create and manage successful machine learning projects. You will learn about Convolutional networks, Recurrent Neural Networks, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. Throughout the semester, you will work on a project of your choosing either individually or in a group and receive guidance and feedback from teaching staff. The class concludes with a project presentation from each group and an award presentation for the best projects.
Instructor
Dr. Felix Gonda
Assistant Professor, Computer Science
E-mail: uojdeeplearning@gmail.com
Meeting: Click her to schedule a meeting
Assistant
Lodu Bosco
E-mail: uojdeeplearning@gmail.com
Required Textbook
A free online version of this book is available at: https://www.deeplearningbook.org and a pdf version can be downloaded by clicking on the book image.
Lecture
Tuesday: 12pm
Location: Senate Hall at UoJ main campus.
Laboratory
Thursday: 2pm
Location: The new UoJ Computer Laboratory
Prerequites
- Linear Algebra: Background in matrices, vectors, and linear equations will come handy when you design models for classification, regression, etc.
- Programming: Some programming experience, such as knowledge gain from taking an introductory course to programming is required.
- Statistics: Statistics will help you extract insights from your raw data and is a valuable skill for a deep learning specialist.