COMP 487: Deep Learning

Course Information

General Information

Credit Hours

• 3

Prerequisites

• COMP 379: Machine Learning or COMP 479: Machine Learning

• Coursework in basic calculus, statistics, and linear algebra

About

This course will cover techniques involved in deep learning.

Description

Deep learning is part of a broader family of machine learning methods based on artificial neural networks. This course will include key concepts of neural network algorithms as well as their applications in computer vision and natural language processing. The topics will include popular building blocks of neural networks including fully-connected, convolutional, recurrent, and transformer layers.

Outcome

Students will: * Analyze popular modern neural architectures such as convolutional and recurrent neural networks * Implement convolutional and recurrent neural network models using such frameworks as Keras and PyTorch * Explore applications of deep learning to computer vision and natural language processing * Design and evaluate their own neural network models * Apply neural network models to a practical task in the context of a term project * Describe their findings in progress reports and a final paper

Syllabi

See the Current Course Syllabi.