Danna Gurari

---

Date	Topics (lecture slides hyperlinked)	Assigned Readings (due prior to class)	Assignments (due prior to class and posted on Canvas)
Tue, Jan 14	Course Introduction
Thur, Jan 16	Artificial Neurons	Ch. 1 of Goodfellow book; Ch. 4-4.2 of Kamath book
Tue, Jan 21	Feedforward Neural Networks and Objective Functions	Ch. 5.1 and Ch. 6-6.1 and 6.3-6.4 of Goodfellow book
Thur, Jan 23	Training Neural Networks with Gradient Descent	Ch. 5.9-5.10, Ch. 6.5-6.6, and Ch. 8-8.1 of Goodfellow book
Tue, Jan 28	Training Optimization	Ch. 8.2-8.5 of Goodfellow book	Problem Set 1
Thur, Jan 30	Model Capacity, Regularization, and Hyperparameters	Ch. 5.2-5.6, Ch. 7-7.4 and 7.8, and Ch. 9 of Goodfellow book
Tue, Feb 4	Convolutional Neural Network (CNN) Basics	Ch. 7.9 and Ch. 9-9.4 and 9.10 of Goodfellow book	Problem Set 2
Thur, Feb 6	“Deep” CNNs for Image Classification: Catalyst for Deep Learning Revolution	Ch. 7.11-7.12, Ch. 8.7.1, and Ch. 9.10 of Goodfellow book
Tue, Feb 11	Dataset Challenges and Hardware Accelerators
Thur, Feb 13	Dense Prediction with CNNs	Ch. 9.6 of Goodfellow book	Lab Assignment 1
Tue, Feb 18	Recurrent Neural Networks	Ch. 10-10.2, 10.7, and 10.10-10.11 of Goodfellow book
Thur, Feb 20	Tokenization and Neural Embeddings	Ch. 3.2-3.3 and 5.1-5.4 of Kamath book	Problem Set 3
Tue, Feb 25	Introduction to Attention	Ch. 7.5.1-7.5.2 of Kamath book; Ch. 10.3-10.5 of Goodfellow book
Thur, Feb 27	Transformer Basics	Ch. 3.10, 7.5.4, and 9.2.6-9.2.10 of Kamath book
Tue, Mar 4	Pioneering Transformers	Ch. 3.8, 3.11, 10-10.3.3 of Kamath book	Lab Assignment 2
Thur, Mar 6	Vision-Language Tasks: Image Captioning and Visual Question Answering	VQA: Visual Question Answering
Tue, Mar 11	Audio Processing, Internet-Scale Training Data, and Scaling Laws	Ch. 8-8.5 of Kamath book	Problem Set 4
Thur, Mar 13	Foundation Models and Prompts	Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
Tue, Mar 18	Tuning Foundation Models (Josh Myers-Dean; PhD student at CU Boulder)	Towards a Unified View of Parameter-Efficient Transfer Learning
Thur, Mar 20	Practical Systems-Level Development Challenges		Lab Assignment 3
Tue, Mar 25	No Class (Spring Break)
Thur, Mar 27	No Class (Spring Break)
Tue, Apr 1	Model Compression
Thur, Apr 3	Learning Faster: Curriculum Learning and Dataset Distillation
Tue, Apr 8	Learning with Less Supervision: Self-Supervised Learning and Active Learning
Thur, Apr 10	Responsible Deep Learning		Final Project Outline
Tue, Apr 15	Responsible Deep Learning
Thur, Apr 17	Future of Deep Learning
Tue, Apr 22	Deep Learning in Industry (Mehrnoosh Sameki; Responsible AI and Generative AI Evaluation Tools Lead at Microsoft)
Thur, Apr 24	Deep Learning in Industry (Suyog Jain; Research Scientist at Meta)
Tue, Apr 29	Course Summary		Final Project Presentation
Thur, May 1	Final Project Presentations		Peer Evaluation
Wed, May 7	No Class (Final Exam Week)		Final Project Report

Overview

The goal of this project is for you to apply what you have learned to a topic of your interest. This will be a self-designed project, under the constraint that it must involve neural networks and deep learning. If you are struggling to choose a topic, we encourage you to attend office hours with the TAs to get assistance. Popular themes in the past include:

• Evaluating the impact of tweaking existing models or offering new model designs for existing dataset challenges
• Analyzing the performance of existing model designs on new datasets
• Testing an existing model in a new form, such as its speed and computational demands on an edge device (e.g., mobile phone) or humans’ experiences with it an application
• Surveying a topic, offering a snapshot of what is the state-of-the-art and discussing open challenges for future research to explore

This effort will include an interim milestone to facilitate your progress (project outline) and culminate in a final report summarizing your work as well as a presentation where you share about your work to your peers. You are welcome to combine this course project with your other course or research efforts as long as you receive permission from the other stakeholders and clarify in all submissions what portion is being counted for this course (and so cannot be counted for your other efforts).

You are strongly encouraged to work with a partner, but can work alone with approval from a teaching assistant. We will host several opportunities throughout the month of March to facilitate finding a partner.

Your final project will constitute 30% of your total class grade. Your project grade will be calculated as follows:

Assignment	% of Final Project Grade
Project outline	20%
Final project presentation	20%
Peer evaluation	10%
Final project report	50%

---

Project Outline

The project outline should map out the entire project.

You will be expected to submit:

• A detailed project outline as a PDF that is 3-4 pages long (excluding references). Only one member of your group is required to submit the PDF, but both group members are welcome to submit the PDF to avoid any potential submission issues.

When choosing your topic, general guidelines are to:

• Choose a problem you have an idea for how to solve
• Choose a problem someone else cares about
• Choose a problem that is not yet solved (review current literature!)
• Choose a problem that you can objectively evaluate by tying it to a task

For the PDF submission, please use a latex template from a mainstream conference or journal, such as ECCV. A great latex paper editor is Overleaf. The outline should include each of the following:

• Title for your project
• [Section 1] Introduction
  • Paragraph 1: Explain the motivation for your work; e.g., Why anyone should care? What are the desired benefits?
  • Paragraph 2: Explain why existing solutions are inadequate for the motivated problem; e.g., Is there a gap in what exists? Is there a weakness in existing approaches?
  • Paragraph 3: Explain what you are proposing, what is new about your idea, and why you believe this solution will be better than previous solutions; e.g., Are you asking a new question, establishing a new methodology to solve a problem, building a new software tool, or offering greater understanding about existing methods/tools?
• [Section 2] Related Work
  • Identify 2-4 related topics. Then, for each topic, cite 2-4 related papers (must include the bibliography). Finally, for each cluster of related works, give a 1-2 sentence explanation describing the key difference(s) of your proposed idea to the cluster of prior works. One way to format each topic is as follows:
    
    Topic:
    Reference 1
    Reference 2
    Reference 3
    Reference 4
    
    Our work is different from these works because…
• [Section 3] Methods – describe the implementation of your proposed idea (e.g., description of your model, system, or how survey papers will be collected) so that:
  • A reader could reproduce your set-up
  • A reader could understand why you made your design decisions
• [Section 4] Experiments – describe 1-2 experiments or analyses you plan to conduct in order to demonstrate/validate the target contribution(s) of your work. Your description should be detailed enough so that a reader could reproduce it. Your description should include the following for each experiment:
  • Main purpose: 1-3 sentence high level explanation
  • Evaluation Metric(s): which ones will you use and why?
• Bibliography: this must be formatted correctly.

Please note that your proposed project is not a binding contract. You will continue to update and improve it as you learn more from your readings and/or feedback.

Final Project Presentation

The final project presentation should be submitted as a zip file which include two parts:

• Text document indicating a URL to a 4 minute recorded video
• PDF document of a poster

Both deliverables should convey the following:

• Motivate the problem your work is designed to solve.
• (Very) briefly explain what other solutions are available and why they are not suitable.
• Demo your idea, approach, and key design decisions.
• Highlight key findings from your experiments and offer insights into what your work has taught us. Focus on finding 1-3 punchlines that explain why your work is exciting/valuable.

Please design your video for an audience who has not taken the class (i.e., lay audience). In other words, your mom, dad, friend, or a potential employer should be able to watch it and understand what you did and why what you did is valuable. You must submit a URL (either public or unlisted) that links to your video in your Canvas submission. To support inclusion of your presentation in our online forum, provide video links to either YouTube or Vimeo. Please verify viewing permissions are set properly before submission or your grade will be penalized.

Your poster should provide a concise framework for you to communicate about your project to a lay audience. In other words, your mom, dad, friend, or a potential employer should be able to see it and understand what you did and why what you did is valuable. If you would like to work from a template, the following are suggested by popular conferences for computer vision material: CVPR, NeurIPS, and ECCV. Alternatively, you can follow general suggestions for how to create a Better Scientific Poster.

On the last day of class, we will gather in an online forum so that students can present their work and learn about other students’ works. We will use the online platform, Gather, where every team’s video and poster will be posted. During this class session, students will be allowed to both stay in their designated spaces to present their poster/videos while answering any questions as well as to visit other students’ designated locations to learn about their work by reviewing their posters and/or videos.

Peer Evaluation

Every student will evaluate the presentation for one third of the projects in the course at the link shared by the course staff (i.e., this is not a team effort). The evaluations will be done during the day of the last class meeting. The evaluations that you do for other students’ projects will not affect your own grade, except that you will be penalized if you do not complete an evaluation (following the requirements) for each assigned group. You do not need to complete an evaluation for your own project.

Final Project Report

For the final project submission, you should submit a final report that is at least 7 pages long (excluding references). It should include each of the following:

• Title
• Abstract – one paragraph summary of your paper describing the motivation, problem, conducted experiments, and experimental findings
• [Section 1] Introduction (as needed, improve upon the material from your project outline)
• [Section 2] Related Work (as needed, improve upon the material from your project outline; if you have not already, you should remove the bulleted structure you used in the initial proposal and instead have a paragraph form)
• [Section 3] Methods (as needed, improve upon the material from your project outline)
• [Section 4] Experiments
  • As needed, improve upon the material from your project outline
  • Report the experimental results, what general trends are observed, and insights/speculations into why your results may be turning out the way they are.
  • Also include at least one paragraph explaining what questions are not fully answered by your experiments and natural next steps for this direction of research.
• [Section 5] Conclusions
  • Summarize in one paragraph what is the main take-away point from your work.
  • Add a final paragraph discussing any potential ethical implications of your project (e.g., fairness, accountability, transparency, privacy, social impact, etc).
• [Section 6] Bibliography

This document is a revision of your project outline. Consequently you only need to expand on the content submitted from the project outline.