Lecture and section information
INFO 1998, Fall 2019
Lecture time: Wed 5:30pm - 6:30pm
Lecture location: Olin 155
Staff and office hours
Lecturer: Tanmay Bansal
- Thursday: 3:30pm - 4:30pm, Rhodes 503
Lecturer: Dylan Tsai
- Tuesday: 1:15pm - 2:15pm, Rhodes 405
Please don’t e-mail any of the TAs directly, unless necessary. All questions / queries for help should be done in person during office hours, or on the course Piazza. If there is something urgent going on, we recommend emailing the course manager.
TA: Ang Jia Jiunn
- Monday: 2:30pm - 3:30pm, Rhodes 503
TA: Camilo Cedeno-Tobon
- Tuesday: 3:00pm - 4:00pm, Rhodes 503
TA: Chris Elliott
- Wednesday: 2:00pm - 3:00pm, Rhodes 412
TA: Samantha Cobado
- Wednesday: 2:00pm - 3:00pm, Rhodes 503
1 credit. S/U Only. The goal of this course is to provide you with a high-level exposure to a wide range of Data Science techniques and Machine Learning models, for the purpose of enabling you to solve real problems with machine learning. The course covers getting set up, manipulating and visualizing large datasets, building supervised and unsupervised machine learning models, and a discussion about the various application of these methods in the real world. If you have religiously followed the course throughout the semester, you should expect to have a high-level and intuitive understanding of how data problems could be tackled. You can apply this quick implementation-oriented toolkit you develop yourself to a variety of fields and problems.
If you are interested in a solid mathematical foundation for data science and machine learning, this class is not sufficient in itself. This course, however, should serve as a head start for you.
No prerequisites; Basic Python experience (at the level of CS 1110) is encouraged.
- We will be working together on in-class assignments/exercises during lectures, so please bring a laptop (or tablet) to fully participate.
- You will need a conda environment and/or virtualenv setup with necessary Python libraries.
- Please refer to the Getting Started page for more information.
Class material will be posted on our course website, including the assignments, lecture slides, notes, and demos.
We will use CMS for assignment / project submissions and feedbacks.
There will be one in-class assignment per lecture, 10 total throughout the semester. All assignments will be done individually. The assignment will be released at the beginning of the lecture (5:30pm ET on Wednesday), and will be due 5:30pm ET next Wednesday (before the start of the following lecture). Each assignment is of reasonable length that we will be able to cover it in lecture (with one additional homework question), but never force yourself to finish it quickly, and don’t let it disturb you from lecture!
Feedback and Grade Postings
We will be providing you with feedback on the Cornell University Course Management System (CMS). We will grade your work as soon as reasonably possible, latest by Sunday midnight.
This is a 1-credit S/U class. In order to get a Satisfactory (S) grade, you will need at least 70%.
There are three components to grading:
- Weekly Assignments (50%): As described above. You may skip up to one assignment.
- Mid-Semester Group Project (15%): There will be a mid-semester project around mid-October. More guidelines will be released on Piazza.
- Final Group Project (35%): There will be an open-ended final project near the end of the semester as part of CDS Hackathon. You will need to choose your own competition / research topic and form a group to work together. Project will be graded based on completion with sufficient amount of effort, and the top teams will receive prize.
This is a student-run course, so we understand how stressful classes can get. Above all, we want you to enjoy learning and applying the course content. So if you are concerned about passing this class, or have any reasonable cases to make for deadline extensions, please reach out the course manager or post a private note on Piazza immediately. We would love to see you succeed, but can only help if you notify us in time.
Attendance is required. We discuss the answers to the assigned assignments in class, and coming to lectures ensures at least a fairly high score on assignments.
All Cornell students are expected to follow the Cornell University Code of Academic Integrity (http://cuinfo.cornell.edu/aic.cfm). Do not refer to notes from previous semesters or data science projects available online. Our instructors have caught these in the past and the penalty for plagiarism is an unsatisfactory (U) grade.