CSCI 5800-003: Deep Learning

Course Description

This course provides a foundation on deep learning – currently the most sought-after skills in machine learning. Students will gain both theoretical and practical understanding of the concept and will work on few real-world problems like location identification from photos (without GPS meta), speech reading / lip reading from silent videos, sign language recognition for your smartphones, stock market forecasting, image/object recognition from surveillance footage. Theoretical concepts include:

  • Introduction to Artificial Neural Network design and learning algorithms

  • Restricted Boltzmann machine design, learning and applications in dimensionality reduction, classification, regression, feature extraction and collaborative filtering.

  • Principles of Convolution neural network, its architecture, variations and applications.

  • Recurrent Neural network, Long short term memory.

  • Deep reinforcement learning algorithms

  • Autoencoders and understand unsupervised neural network architectures.

  • Understand the ever-evolving computational frameworks for deep neural networks, like TensorFlow, Keras, PyTorch, etc, and how to build a custom framework.

Teaching Staff


Teaching Assistants

  • Crystin Rodrick

    • Office: LW-835

    • Office hours: Thursday 9am-12pm or by appointments.

Please use Piazza for communication with the teaching staff including making an appointment. See the explanation below on this page.

Time and Location


Mon & Wed 2:00pm-3:15pm


It is recommended that you choose the following primary textbook.

Picture of the Primary Textbook 


This term we will be using Piazza for class announcements and discussion. The system is highly catered to getting you help fast and efficiently from classmates, the TA, and myself. Rather than emailing questions to the teaching staff, I encourage you to post your questions on Piazza. If you have any problems or feedback for the developers, email
Find our piazza class page at:
All enrolled students should have received invites from piazza. If not, please let me know as soon as possible.


Canvas will only be used for online assignment submissions, online quizzes, and communicating grades on assignments and exams and for distributing solutions (not intended for the eyes of future students).