Overview
Course description: This course will cover the basics of modern deep neural networks. The first part of the course will introduce neural network architectures, activation functions, and operations. It will present different loss functions and describe how training is performed via backpropagation. In the second part, the course will describe specific types of neural networks, e.g. convolutional, recurrent, graph networks and transformers, as well as their applications in computer vision and natural language processing. The course will also briefly discuss reinforcement learning and unsupervised learning, in the context of neural networks. In addition to attending lectures and completing bi-weekly homework assignments, students will also carry out and present a project.Prerequisites: Math 220 (Calculus I), Math 280 or 1180 (Linear Algebra), CS 1501 (Algorithm Implementation)
Piazza: Sign up for it here. Please use Piazza rather than email so everyone can benefit from the discussion-- you can post in such a way that only the instructor sees your name. Please try to answer each others' questions whenever possible. The best time to ask the instructor or TA questions is during office hours.
Programming language/framework: We will use Python, NumPy/SciPy, and PyTorch.
Textbooks: We will have required readings from the following textbook.
- Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning. MIT Press, 2016. online version
- Aston Zhang, Zack C. Lipton, Mu Li, and Alex J. Smola. Dive into Deep Learning. 2019. online version
- Michael Nielsen. Neural Networks and Deep Learning. 2019. online version
- Eugene Charniak. Introduction to Deep Learning. MIT Press, 2019. link
- Christopher M. Bishop. Pattern Recognition and Machine Learning. Springer, 2006. free pdf
- Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. MIT Press, 2012.
- Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning. Springer, 2009. link
- David Barber. Bayesian Reasoning and Machine Learning. Cambridge University Press, 2012. link
- Dan Jurafsky and James H. Martin. Speech and Language Processing. online version
- Richard Szeliski. Computer Vision: Algorithms and Applications. online version
Policies
Grading
Grading will be based on the following components:- Homework (3 assignments x 15% each = 45%)
- Project (5% proposal + 10% first report + 10% second report + 15% presentation = 40%)
- Quizzes (20x0.5% = 10%)
- Participation (5%)
Assignment Submission Mechanics
Homework, project reports and presentations slides are due at 11:59pm on the due date. You will submit your homework using Canvas, under "Assignments" and the corresponding homework ID. You should submit a single zip file with source/results/report/slides, as requested. Name the file YourFirstName_YourLastName.zip. Please comment your code! Grades will be posted on Canvas.Note that Canvas will also contain an automatically computed running average column that you can use to gauge how you're doing in the class based on grades that are already available. Generally, Overall scores over 90% map to some type of A, over 80% to B, and over 70% to C.
Exams and Quizzes
There will be no exams. However, we will have almost daily low-stakes quizzes to be completed after class (open-book).Participation
Students are expected to regularly attend the class lectures, and should actively engage in in-class discussions. Attendance will not be taken, but keep in mind that if you don't attend, you cannot participate. You can actively participate by, for example, responding to the instructor's or others' questions, asking questions or making meaningful remarks and comments about the lecture, answering others' questions on Piazza, or bringing in relevant articles you saw in the news. The grading rubric will be as follows: 1 = you attended infrequently, 2 = you attended frequently but did not speak in class, 3 = you attended frequently and spoke a few times, 4 = you participated frequently, 5 = you participated every other week or more.Homework Late Policy
For homework assignments only (not for project components), you get 3 "free" late days counted in minutes, i.e., you can submit a total of 72 hours late. For example, you can submit one homework 12 hours late, and another 60 hours late. The 72-hour "budget" is total for all assignments, NOT per assignment. Once you've used up your free late days, you will incur a penalty of 25% from the total assignment credit possible for each late day. A late day is anything from 1 minute to 24 hours.Collaboration Policy and Academic Honesty
You will do your work (homework and quizzes) individually. The work you turn in must be your own work. You are allowed to discuss the assignments with your classmates, but do not look at code they might have written for the assignments, or at their written answers. You are also not allowed to search for code on the internet, use solutions posted online unless you are explicitly allowed to look at those. When in doubt about what you can or cannot use, ask the instructor! Plagiarism will cause you to fail the class and receive disciplinary penalty. Please consult the University Guidelines on Academic Integrity. All project components involve group work.Note on Disabilities
If you have a disability for which you are or may be requesting an accommodation, you are encouraged to contact both your instructor and Disability Resources and Services (DRS), 140 William Pitt Union, (412) 648-7890, drsrecep@pitt.edu, (412) 228-5347 for P3 ASL users, as early as possible in the term. DRS will verify your disability and determine reasonable accommodations for this course.Note on Medical Conditions
If you have a medical condition which will prevent you from doing a certain assignment, you must inform the instructor of this before the deadline. You must then submit documentation of your condition within a week of the assignment deadline.Statement on Classroom Recording
To ensure the free and open discussion of ideas, students may not record classroom lectures, discussion and/or activities without the advance written permission of the instructor, and any such recording properly approved in advance can be used solely for the student's own private use.[top]
Project
Please enter your team information and topic here when you submit the project proposal.The project is expected to be a new method for an existing problem or an application of techniques we studied in class (or another method) to a new problem that we have not discussed in class. Below are some tips:
- The project should include some amount of novelty. For example, you cannot just re-implement an existing paper or project. You are allowed to use existing code for known methods, but your project is expected to be a significant amount of work and not just a straight-up run of some package.
- You must show that your method is in some sense better (quantitatively) than at least some relatively recent existing methods. For example, you can show that your method achieves superior accuracy in some prediction task compared to prior methods, or that it achieves comparable accuracy but is faster. This outcome is not guaranteed to come out the way you intended during the limited timespan of a course project, so whether or not your outperform the state of the art will only be a small component of your grade. Further, if you propose a sufficiently interesting method, rather than an extremely simple method, it will be less of a problem if your method does not outperform other existing approaches to the problem.
- You are encouraged to use any external expertise you might have (e.g. biology, physics, etc.) so that your project makes the best use of areas you know well, and is as interesting as possible.
- Students are required to work in groups of three or four for their final project.
- A sample list of topics you can (but don't have to) choose from is provided on Canvas. The instructor has suggested these based on her familiarity with the literature, and these contain sufficient amount of novelty, with a risk level appropriate for this course. At the very list you should read through this list carefully to get a sense of what an appropriate topic might be.
- Milestones for the project include: (1) project proposal, (2) first mid-semester report, (3) second mid-semester report, (4) final presentation.
- You will submit a project proposal that describes what you propose to do; why what you propose to do is interesting, important, and challenging; what data and resources you are going to use; what your high-level idea of the method is; and how you plan to evaluate your method, including against what baselines. A grading rubric is provided below.
- There will be two mid-semester reports per team. The first will focus on motivation, related work (i.e. detailed literature review), and your proposed approach. The goal is to have designed your method conceptually, and to have made some progress in terms of implementing this proposed method. For both reports, do comment on challenges you are facing. A good source for learning about what work has been done in your domain of interest are search engines, Google Scholar, and arxiv.org.
- The second mid-semester report should describe the progress you've made since the first report, including a mature formulation of your method, and ideally some experimental results for your method.
- The final presentation will focus on your experimental validation and findings, including comparisons to relevant baselines. In your presentation, make sure to describe your motivation for the work, as well as relevant prior literature, briefly, and of course your method.
- Your proposal, reports and slides (for the presentation) are due on Canvas on the indicated due date (see the schedule), at 11:59pm. Note you cannot use free-late-days for project components.
- Your grades will be based on four rubrics, available below. For the presentation, your grade will be an average of (1) your classmates' scores, and (2) the instructor's scores.
- Combining your final project for this class and another class is generally permitted, but the project proposal and final report should clearly outline what part of the work was done to get credit in this class, and the instructor should approve the proposed breakdown of work between this and another class.
- The presentation should take 12-15 minutes, with 1-2 minutes for questions. Make sure to test your laptops before class as we'll have an extremely tight schedule! The time budgeted for laptop switching is on the order of seconds.
- You are allowed to change your final presentation slides (e.g. to include new results) until the slide submission deadline, but please mark new content in yellow.
- What do you propose to do?
- What have others attempted in this space, i.e. what is the relevant literature?
- Why is what you are proposing interesting?
- Why is it challenging?
- Why is it important?
- What data do you plan to use?
- What is your high-level idea of how your method will work?
- In what ways is this method novel?
- How will you evaluate the method, i.e. what metrics are you going to use, and what baselines are you going to compare to?
- Give a (1) conservative and (2) an ambitious schedule of milestones for your project.
- What is the prior work in this space? Describe in detail (2-3 pages, in your own words) (1-10 points).
- How is your work novel, in the context of this prior work? (1-5)
- What is your proposed approach? Describe in detail (3-4 pages). (1-10)
- Why should your approach work well for this task? (1-5)
- In what ways is your proposed approach ambitious? (1-5)
- How do you plan to evaluate your method, against what baselines? (It's possible these will have changed after the proposal stage.) (1-5)
- What progress have you made since the first report? Describe in detail (1-2 pages). (1-10)
- What challenges have you encountered along the way? (1-5)
- What are your next steps? Describe in detail (1-2 pages). (1-10)
- What metrics are you going to use to evaluate your method? What datasets are you going to use? What are your experimental results so far, if any? (1-5)
- How well did the authors (presenters) explain what problem they are trying to solve? (1-5 points)
- How well did they explain why this problem is important and/or challenging? (1-5)
- How clearly was prior work described? How well did the authors explain how their proposed work is different than prior work? (1-5)
- How clearly did the authors describe their proposed approach? (1-10)
- How novel and ambitious is the proposed approach? (1-5)
- How well did the authors describe their experimental validation? How informative were the figures used? (1-5)
- Were all/most relevant experimental settings (e.g. datasets, tasks) and baselines (competitor methods) included in the experimental validation? (1-5)
- To what extent is the performance of the proposed method satisfactory? (1-5)
- How informative were the conclusions the authors drew about their method’s performance relative to other methods? How sensible was the discussion of limitations? How interesting was the discussion of future work? (1-5)
- Suggested list on Canvas.
- Look at the datasets and tasks below.
- Look at the topics in the programs of some of the recent computer vision conferences: CVPR 2020 (with papers downloadable here) and ICCV 2019 (with papers here).
- Check out project resources and topics in a related class here.
- Read some paper abstracts on this page.
Schedule
| Date | Topic | Readings | Lecture slides | Due |
| 1/19 | Introduction, administrivia, ML overview/review | DL Ch
1-5, Bishop PRML Sec. 1.1, Bishop PRML Sec. 7.1 |
pptx pdf | |
| 1/21 | ||||
| 1/26 | ||||
| 1/28 | Neural network basics (tasks, operations, training) | DL Ch 4.2, 4.3, 6, Bishop Ch 5 |
pptx pdf exercise answers | |
| 2/2 | ||||
| 2/4 | proposal due | |||
| 2/9 | PyTorch tutorial (TA) [links on Canvas] | aaaa | ||
| 2/11 | ||||
| 2/16 | Training part 2 (alternative notation, optimization, properties, convergence) | DL Ch 7, 8, 11 | pptx pdf | |
| 2/18 | HW1 due | |||
| 2/25 | ||||
| 3/2 | Convolutional neural networks (architectures, visualization, applications) |
DL Ch 9 | pptx pdf | report 1 due |
| 3/4 | ||||
| 3/9 | ||||
| 3/11 | Recurrent neural networks (architectures, training, applications) | DL Ch 10, RNN blog 1, RNN blog 2, RNN vis | pptx pdf | |
| 3/16 | ||||
| 3/18 | HW2 due | |||
| 3/23 | Transformers (self-attention in language and beyond) | Mikolov NIPS 2013, Vaswani NIPS 2017, Devlin NAACL 2019, Illustrated Transformer and BERT, and Dosovitskiy ICLR 2021, Lu NeurIPS 2019 | pptx pdf | |
| 3/25 | ||||
| 3/30 | report 2 due | |||
| 4/1 | Advanced topics (graph networks, unsupervised and reinforcement learning, generation, ethics) | Kipf GCNs, Doersch ICCV 2015, Karpathy RL blog, Mnih NIPS-W 2013, Goodfellow NIPS 2014, Bolukbasi NIPS 2016, Hendricks ECCV 2018 | pptx pdf | |
| 4/6 | ||||
| 4/8 | HW3 due | |||
| 4/13 | ||||
| 4/15 | Project presentations | |||
| 4/20 | participation notes | |||
| 4/22 | slides due |
[top]
Resources
This course was inspired by the following courses:- Convolutional Neural Networks for Visual Recognition by Fei-Fei Li, Justin Johnson, and Serena Young, some content by Andrej Karpathy, Stanford University, Spring 2019
- Natural Language Processing with Deep Learning by Chris Manning, Abigail See, based on an earlier course by Richard Socher, Stanford University, Winter 2019
- Introduction to Deep Learning by Bhiksha Raj, Carnegie Mellon University, Fall 2019
- Introduction to Machine Learning by Rebecca Hwa, University of Pittsburgh, Fall 2015
- Machine Learning by Milos Hauskrecht, University of Pittsburgh, Spring 2015
- Introduction to Machine Learning by Dhruv Batra, Virginia Tech, Spring 2015
- Machine Learning by Tommi Jaakkola, MIT
- Machine Learning by Subhransu Maji, UMass Amhrest, Spring 2015
- Machine Learning by Erik Sudderth, Brown University, Fall 2015
- Computer Vision by Kristen Grauman, UT Austin, Spring 2011
- Computer Vision by Derek Hoiem, UIUC, Spring 2015
- Natural Language Processing by Ray Mooney, UT Austin
- Microsoft COCO (Common Objects in Context) (object recognition, segmentation, image description)
- ImageNet (object recognition)
- SUN Database (scenes)
- Caltech-UCSD Birds 200 (fine-grained object recognition)
- MSRC Annotations (active learning)
- Animals with Attributes (attribute-based recognition)
- a-Pascal + a-Yahoo (attribute-based recognition)
- Shoes (attribute-based search)
- INRIA Movie Actions (action recognition)
- ADL (ego-centric action recognition)
- Action Quality (evaluating action quality)
- CarDb Historical Cars (style classification of cars)
- Recognizing Image Style (photographic style classification)
- Judd gaze (visual saliency prediction)
- Visual Persuasion (predicting subtle messages in images)
- Advertisements: Images and Videos (understanding what the ad prompts of the viewer and why)
- VQA (visual question-answering)
- Recognition datasets list compiled by Kristen Grauman
- Human activity datasets list compiled by Chao-Yeh Chen
- TensorFlow (deep learning framework by Google)
- Caffe (deep learning framework by Yangqing Jia et al.)
- PyTorch (another popular deep learning framework)
- Keras (deep learning library)
- LIBSVM (by Chih-Chung Chang and Chih-Jen Lin)
- SVM Light (by Thorsten Joachims)
- VLFeat (feature extraction, tutorials and more, by Andrea Vedaldi)