Vector Institute - Deep Learning I

_DUE TO COVID-19 CONCERNS AND POLICIES, WE HAVE POSTPONED THIS CLASS UNTIL THE FALL, EXACT DATES TO BE DETERMINED. __FOR INQUIRIES, EMAIL: NATALIE.KLYM@VECTORINSTITUTE.AI_   VECTOR INSTITUTE AI CERTIFICATE COURSES FOR INDUSTRY   DEEP LEARNING I: NEURAL NETWORKS AND SUPERVISED LEARNING    AVAILABLE TO VECTOR INSTITUTE SPONSORS [https://vectorinstitute.ai/#partners] ONLY   FOR REGISTRATION INQUIRIES, EMAIL: NATALIE.KLYM@VECTORINSTITUTE.AI   DATE: Mar 17 - May 5, 2020 (Classes run Tuesdays, 10 a.m. - 2 p.m.), final assignment due May 19, 2020   LOCATION: Vector Institute, MaRS Building, 661 University Ave Suite 710, Toronto, ON M5G 1M1   INSTRUCTORS:  Alireza Makhzani [https://vectorinstitute.ai/team/alireza-makhzani/], Mengye Ren [https://www.cs.toronto.edu/~mren/]   FEES: TOTAL COURSE FEE: $5,000    (A deposit of $250 will be collected upon registration. $4,750 will be invoiced upon course commencement.)   Must read: Terms and Conditions [https://drive.google.com/open?id=1pgRLYR68Y5kGWw0qIMk5WOLC1Sn0Qz4q]     COURSE OVERVIEW   The Deep Learning I: Neural Networks and Supervised Learning course provides an overview of the foundational ideas and recent advances in neural net algorithms with a focus on supervised learning. Created by Roger Grosse [https://vectorinstitute.ai/team/roger-grosse/], Canada CIFAR AI Chair & Vector Faculty Member, the course provides participants with an in-depth understanding of how algorithms behave, how to derive algorithms mathematically, implement them from scratch, build and troubleshoot a neural network, and confidently construct a chat-bot using neural networks. The curriculum includes industry discussions to help participants understand how to deploy neural networks in their organizations.   WHO SHOULD ATTEND   * Employees working as/or having experience as Data Scientists, Data Engineers, machine learning (ML) Engineers, ML Researchers or closely related roles, and who meet the criteria outlined in the prerequisites. * Participants are responsible for ensuring they have the required background for the course. We have provided a short self-assessment quiz [https://drive.google.com/file/d/12-MvbwSTg7ltPF9bLt6Ui-v_L0ksCYdI/view].   AVAILABLE TO VECTOR INSTITUTE SPONSORS [https://vectorinstitute.ai/#partners] ONLY   LEARNING OUTCOMES   At the end of this course participants will be able to: * Recognize use cases and applications of Deep Learning in industry * Confidently construct a neural network solution at work to create value or solve a problem * Confidently construct a chat-bot using neural networks * Recognize errors, trouble-shoot and debug errors in a neural network * Conversationally describe what they did in this course to a technical and non-technical audience at work   PREREQUISITES   * Multivariable Calculus * Linear Algebra * Probability and Statistics * Experience with ML algorithms, such as logistic regression, decision trees, nearest neighbors * Programming experience (Python recommended)   COURSE LOAD   Participants can expect to spend a total of 10-15 hours per week attending Lectures, Tutorials, Industry Discussions, and completing assignments.     INSTRUCTORS   ALIREZA MAKHZANI [https://vectorinstitute.ai/team/alireza-makhzani/] is a Vector Faculty Member and CIFAR Artificial Intelligence Chair. Alireza completed his PhD in Electrical & Computer Engineering at the University of Toronto in 2017. His most recent research focuses on generative models and their applications in semi-supervised learning; neural networks that can learn sparse representations of data; and deep reinforcement learning algorithms. During his PhD, he interned for the Google Brain Team in 2015 where he worked on generative models of images; and Google DeepMind in 2016 where he worked on developing deep reinforcement learning algorithms for the StarCraft II game. Alireza completed his Master’s at the University of Toronto in 2012 and received his Bachelor’s degree from Amirkabir University of Technology (Tehran Polytechnic) in Iran in 2010.   MENGYE REN [https://www.cs.toronto.edu/~mren/] is a PhD student at VECTOR AND IN THE MACHINE LEARNING GROUP OF THE DEPARTMENT OF COMPUTER SCIENCE AT THE UNIVERSITY OF TORONTO. His academic advisor is Prof. Richard Zemel [http://www.cs.toronto.edu/~zemel/]. He also works as a research scientist at Uber Advanced Technologies Group (ATG) TORONTO, directed by Prof. Raquel Urtasun [http://www.cs.toronto.edu/~urtasun/], doing self-driving related research. During his undergrad, he studied Engineering Science with a focus on Electrical and Computer Engineering at the University of Toronto. He is originally from Shanghai, China.     COURSE OUTLINE & SCHEDULE    _Note that classes run Mar 17-May 5, 2020 with final assignment due May 19, 2020._     WEEK 1: TUESDAY, MAR 17/20 10:00-12:00              Lecture: Introduction (Alireza Makhzani) 11:00-12:00              Lecture: Linear Models (Alireza Makhzani) 12:00-12:30              Lunch 12:30-1:00                Industry Discussion: Andrew Brown, CIBC 1:00-2:00                  Tutorial: TA TBA   Week 2: Tuesday, Mar 24/20 10:00-11:00              Lecture: Multilayer Perceptrons (Alireza Makhzani) 11:00-12:00              Lecture: Backpropagation (Alireza Makhzani) 12:00-12:30              Lunch 12:30-1:00                Industry Discussion: Andrew Brown, CIBC 1:00-2:00                  Tutorial: TA TBA   Week 3: Tuesday, Mar 31/20 10:00-11:00              Lecture: Distributed Representations (Mengye Ren) 11:00-12:00              Lecture: Automatic Differentiation (Mengye Ren) 12:00-12:30              Lunch 12:30-1:30                Tutorial: TA TBA   Week 4: Tuesday, Apr 7/10 10:00-12:00              Lecture: Optimization I (Mengye Ren) 11:00-12:00              Lecture: Optimization II (Mengye Ren) 12:00-12:30              Lunch 12:30-1:00                 Industry Discussion: Andrew Brown, CIBC 1:00-2:00                  Tutorial: TA TBA    Week 5: Tuesday, Apr 14/20 10:00-11:00              Lecture: Convolutional Networks (Mengye Ren) 11:00-12:00              Lecture: Image Classification (Mengye Ren) 12:00-12:30              Lunch 12:30-1:30                Tutorial: TA TBA   Week 6: Tuesday, Apr 21/20 10:00-11:00              Lecture: Optimizing the Input (Mengye Ren) 11:00-12:00              Lecture: Generalization (Mengye Ren) 12:00-12:30              Lunch 12:30-1:30                Tutorial: TA TBA   Week 7: Tuesday, Apr 28/20 10:00-11:00              Lecture: Recurrent Neural Nets (Mengye Ren) 11:00-12:00              Lecture: Exploding and Vanishing Gradients (Mengye Ren) 12:00-12:30              Lunch 12:30-1:30                Tutorial: TA TBA   Week 8: Tuesday, May 5/20 10:00-11:00              Lecture: Attention (Alireza Makhzani) 11:00-12:00              Lecture: Transformers (Alireza Makhzani) 12:00-12:30              Lunch 12:30-1:00                Industry Discussion: Andrew Brown, CIBC 1:00-2:00                  Tutorial: TA TBA