Syllabus (Spring 2023)
Acknowledgements
This class is being funded by a TensorFlow and Google AI award to support machine learning courses and diversity programs.
During the semester students will have access to NVIDIA's Deep Learning Institute materials.
Description
Recent advances in Neural Networks and Deep Learning have made it possible to develop computational solutions to complex tasks usually performed by humans. Nowadays, well-trained Deep Learning architectures are able to achieve comparable or superhuman performance in complex tasks such as image classification/recognition, natural language understanding, speech recognition, machine translation, game playing, autonomous driving, and so forth.
In this course students will learn the fundamentals of deep learning architectures, including convolutional networks, recurrent neural networks, auto-encoders, and generative adversarial networks. Along the way, this course will also provide a basic introduction to basic machine learning topics, such as, supervised/unsupervised learning, gradient descent, generalization and overfitting, regularization, and model selection.
The course is open to advanced Undergraduate students and Graduate students. Students are expected to have good programming skills (preferably Python) and taken courses on machine learning, probability, statistics and linear algebra.
Course Info
- Instructor: Prof. Marco Alvarez
- Lectures: TTh 2 - 3:15p @ CBLS 152
- Office Hours: T 3:30-4:30 @ Tyler 255
Support Tools and Technology
Students in this class will use the following platforms for communication, assignments, and grading. All students are required to use their primary email from eCampus for entering EdStem and Gradescope. We automatically register students.
All lecture materials and readings will be shared @ Ed Discussion
Recommended Textbooks
- The Science of Deep Learning, I. Drori.
- Deep Learning, I. Goodfellow, Y. Bengio, A. Courville.
- Introduction to Deep Learning, E. Charniak.
- Hands-On Machine Learning with Scikit-Learn and TensorFlow, A. Géron
- Deep Learning with Python, F. Chollet.
Grading
| Task | Percentage |
|---|---|
| Assignments (programming, problem sets) | 20% |
| Midterm Exam | 25% |
| Technical Presentation | 20% |
| Final Project | 35% |
Your final letter grade will be calculated using the cutoffs in the table below. These cutoffs might be lowered, but they will not be raised. Your final letter grade will be the letter corresponding to the highest cutoff value less or equal than your final grade. Consider that those values are strict. For example, a final grade of 93.99 is an A- and not an A.
A A- B+ B B- C+ C C- D+ D F
94 90 87 83 80 77 73 70 67 60 0
Academic Honesty
Discussions with others to understand general homework problems and class-related concepts are strongly encouraged. However, when working on assignments, all written work and source code must be your own. You might not look at anyone's written solution. Students are prohibited from accessing or comparing homework answers with those of other students prior to submitting each assignment. Copying another individual solution is plagiarism, a serious offense, and the one most common in computer science courses. Anyone that provides homework answers or source code for a programming assignment to another individual is also guilty of academic dishonesty. Both will be prosecuted in accordance with the University's Policy of Academic Honesty.
Disability Accommodations
Any student with a documented disability is welcome to contact me as early in the semester as possible, so that we may arrange reasonable accommodations. As part of this process, please be in touch with Disability Services for Students Office.
Religious Holidays
It is the policy of the University of Rhode Island to accord students, on an individual basis, the opportunity to observe their traditional religious holidays. Students desiring to observe a holiday of special importance must provide written notification to each instructor.