An introduction to the theory and applications of deep learning. Topics include basic neural networks, convolutional and recurrent networks, and computer vision and language interpretation applications. Students will learn to design neural network architectures and training procedures via hands-on assignments. Credits: 4
Prerequisite(s): COS 285 or COS 422 or permission of instructor.
Learning Outcomes
By the end of this course, students will be able to:
- Demonstrate an understanding of the fundamental concepts and architectures of basic neural networks, convolutional neural networks, and recurrent neural networks.
- Apply deep learning techniques and models to solve practical problems in computer vision and natural language processing.
- Design and implement appropriate neural network architectures for specific applications.
- Analyze and interpret the performance of deep learning models based on evaluation metrics and techniques.
- Construct and train deep learning models from scratch, incorporating appropriate architectures, loss functions, and optimization algorithms.
- Design and implement effective training procedures and hyperparameter tuning strategies for deep learning models.
Textbook
Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2023). Dive into deep learning. Cambridge University Press.
Syllabus
Offered
Fall Semester (Even Years)