Main conferences NIPS CVPR ICML 11 How How Teaching staff Instructor Charles

Main conferences nips cvpr icml 11 how how teaching

This preview shows page 11 - 20 out of 124 pages.

Main conferences: NIPS, CVPR, ICML, . . . 11
Image of page 11

Subscribe to view the full document.

How? How? – Teaching staff Instructor Charles Deledalle Teaching assistants Sneha Gupta Abhilash Kasarla Anurag Paul Inderjot Singh Saggu 12
Image of page 12
How? How? – Schedule 30 × 50 min lectures (10 weeks) Mon/Wed/Fri 3:00-3:50pm Room CENTR 115 Ledden Auditorium (LEDDN) 5 × 2 hour optional labs every two weeks (refer to Google’s calendar) Group 1: Fri 10am-12pm (lastnames from A to Kan) Group 2: Tues 2-4pm (lastnames from Kar to Ra) Group 3: Thurs 10am-12pm (lastnames from Ro to Z) Jacobs Hall, Room 4309 Please, coordinate with your classmates to switch groups. Office hours Charles Deledalle, Weekly on Tues 10am-12pm, Jacobs Hall 4808. TAs, every two other weeks, TBA Google calendar: 13
Image of page 13

Subscribe to view the full document.

How? How? – Assignments / Project / Evaluation 4 assignments in Python/Pytorch (individual) . . . . . . . . . . . . . . . . . . . 40% Don’t wait for the lectures to start, You can start doing them all now. 1 project open-ended or to choose among 3 proposed subjects . . . . 30% In groups of 3 or 4 (start looking for a group now), Details to be announced in a couple of weeks. 3 quizzes ( 45 mins each) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30% Multiple choice on the topics of all previous lectures, Dates are: April 24, May 17, June 10 (3-3:50pm, CENTR 115) No documents allowed. 14
Image of page 14
How? How? – What assignments? Assignment 1 (Backpropagation): Create from scratch a simple machine learning technique to recognize hand-written digits from 0 to 9 . -→ 96% success Assignment 2 (CNNs and PyTorch): Develop a deep learning technique and learn how to use GPUs with PyTorch. Improve your results to 98%! 15
Image of page 15

Subscribe to view the full document.

How? How? – What assignments? Assignment 3 (Transfer learning): Teach a program how to recognize bird species when only a small dataset is available. -→ Mocking bird! 16
Image of page 16
How? How? – What assignments? Assignment 4 (Image Denoising): Teach a program how to remove noise. -→ 17
Image of page 17

Subscribe to view the full document.

How? How? – Assignments and Project Deadlines Calendar Deadline 1 Assignment 0 – Python/Numpy/Matplotlib (Prereq) . . . . . . . . . . . . . . . . optional 2 Assignment 1 – Backpropagation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . April 17 3 Assignment 2 – CNNs and PyTorch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . May 1 4 Assignment 3 – Transfer Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . May 15 5 Assignment 4 – Image Denoising . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . May 29 6 Project . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . June 7 Refer to the Google calendar: 18
Image of page 18
How? How? – Prerequisites Linear algebra + Differential calculus + Basics of optimization + Statistics/Probabilities Python programming (at least Assignment 0) Optional: cookbook for data scientists Cookbook for data scientists Convex optimization Conjugate gradient Let A C n × n be Hermitian positive definite The sequence x k defined as, r 0 = p 0 = b , and x k +1 = x k + α k p k r k +1 = r k - α k Ap k with α k = r * k r k p * k k p k +1 = r k +1 + β k p k with β k = r * k r k r * k r k converges towards A - 1 b in at most n steps.
Image of page 19

Subscribe to view the full document.

Image of page 20

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Ask Expert Tutors You can ask 0 bonus questions You can ask 0 questions (0 expire soon) You can ask 0 questions (will expire )
Answers in as fast as 15 minutes