Claudio Silva

Claudio Silva

Institute Professor, New York University

Visualization for Machine Learning

## Teaching Staff - Instructor: Claudio Silva (csilva@nyu.edu); [webpage](https://ctsilva.github.io) - Section Leader: Erin McGowan (erin.mcgowan@nyu.edu) - Teaching Fellow: Vitoria Guardieiro (vitoria.guardieiro@nyu.edu) - Grader: Rithvik Guruprasad (rg4361@nyu.edu) ## Location Instruction Mode: In-Person Meeting Times: - DS-GA 3001.001 (Lecture) Thursdays 6:45pm-8:25pm Classroom: 31 Washington Pl (Silver Ctr) Room 520 - DS-GA 3001.002 (Lab) Fridays 10:15am-11:05am Classroom: 31 Washington Pl (Silver Ctr) Room 520 ## Discord - Class Discord: [https://discord.gg/6pFj8dMK](https://discord.gg/6pFj8dMK). - All our communications happen here. - Anything related to assignments, grading, etc., send a direct message to Grader(s). - Anything related to labs / coding contact Erin or Vitoria. - Feel free to direct message for anything else. ## Course Prerequisites - Solid programming expertise. - The coursework includes extensive programming with JavaScript and D3.js. To be covered in the labs. - We will also expect students to be able to program in Python. - Basic knowlege of machine learning. ## Course Description - Our course is based on foundations of visual analytics, which is an area of data visualization that is concerned with improving the human analytic process. - Visual analytics is concerned with combining automated processes with human-driven processes that are built around data visualization: visual representations of data, and ways to interact with data. ## Course Objectives - This course is designed to sharpen a student's knowledge of visualization. - We aim to make the student a more effective data scientist. - The course has a major project, which will help the student develop research skills. ## Course Structure - The course include lectures and labs. We will strive to have hands-on sessions to complement theoretical materials. - Starts with a short primer on visualization. - Then we will cover techniques for visualizing model assessment, white-box and black-box machine learning explainers, and dimensionality reduction. - Second half of the course has more advanced topics, including Topology Data Analysis and techniques for visualizing deep neural networks. ## Reading Material * There is no textbook for the course. * We will have suggested reading materials for each class. * Supplemental readings to be used as reference material: - Data Visualization Curriculum, Heer, [link](https://observablehq.com/@uwdata/data-visualization-curriculum) - A Course in Machine Learning, Daume, [link](http://ciml.info/dl/v0_99/ciml-v0_99-all.pdf) - Interpretable Machine Learning, Molnar, [link](https://christophm.github.io/interpretable-ml-book/) - Introduction to Machine Learning, Bernard, [link](https://www.wolfram.com/language/introduction-machine-learning/) - Deep Learning, Goodfellow et al, [link](http://www.deeplearningbook.org/) ## Research Project - Course includes a substantial research project. - Projects are expected to be pursued in groups of 2-3. - Once the group is finalized, students cannot change or separate their groups throughout the semester. ## Course Assessment * Assignments (50%) * Project Proposal (4-page writeup): 10% * Project Updates (1-page writeup): 10% * Full Project (up to 8-page writeup): 25% * Class Participation: 5% ## Late Submissions Late submissions of assignments will be penalized as follows: - A standard deduction rate of 20% per day. It means that after 5 days of being late, your assignment will have a maximum grade of 0 (zero). - You will have a one-time exception for submitting assignments late (up to 5 days late). ## Academic Integrity - All students are expected to do their own work. - See detailed policy on class syllabus. - Also, here is a [link to the GSAS statement on Academic Integrity](https://gsas.nyu.edu/about-gsas/policies-and-procedures/gsas-statement-on-academic-integrity.html). ## AI policy - You can use generative AI tools to do the assignments in this class. - If you use an AI to guide you in completing an assignment, you have to disclose which parts were generated by the AI.  ## NYU Academic Calendar - [link to NYU Academic Calendar](https://www.nyu.edu/students/student-information-and-resources/registration-records-and-graduation/academic-calendar.html?semester=Spring%202024) - This course does not have a final exam, but there will be a final project presentation. - Also, please pay attention to notable dates such as Add/Drop, Withdrawal, etc. ## End of Course Logistics * Any questions? ## BREAK -- 5 minutes ## Self Introduction for VisML 2024 [slides](https://docs.google.com/presentation/d/1lmbWUSjxR45gdMqda9ZYeRVOvpnxB73qAFdEcAFfPoU/edit?usp=sharing)