applied machine learning
play

Applied Machine Learning Syllabus and logistics Siamak Ravanbakhsh - PowerPoint PPT Presentation

Sep 01, 2022 •193 likes •418 views

Applied Machine Learning Syllabus and logistics Siamak Ravanbakhsh COMP 551 (fall 2020) Admin Live Class: Tuesday & Thursday, 10:05 am - 11:25 am Location: Online Zoom Meeting Instructor: Siamak Ravanbakhsh <siamak@cs.mcgill.ca> Office

  1. Applied Machine Learning Syllabus and logistics Siamak Ravanbakhsh COMP 551 (fall 2020)

  2. Admin Live Class: Tuesday & Thursday, 10:05 am - 11:25 am Location: Online Zoom Meeting Instructor: Siamak Ravanbakhsh <siamak@cs.mcgill.ca> Office hours: Thursday, 11:30 am - 12:30 pm 0 0 1

  3. Recorded or live? live classes that are recorded this may change depending on the outcome of first few lectures we may also try flipping the classroom: prerecorded lectures spend more time on the "applied" side COMP 551 | Fall 2020

  4. About you prior to add-drop Mostly third year undergraduates 2nd year undergraduates, look out for prerequisites!

  5. About you prior to add-drop

  6. About me Siamak Ravanbakhsh (pronounced almost like see-a-Mac) Assistant Professor in the School of Computer Science Canada CIFAR AI Chair at Mila research interest: representation learning 0 what is the right representation for an AI agent? how do we learn quickly from data and perform inference two approaches to this problem that I explore using probabilistic (graphical) models using invariances and symmetries I also collaborate with physicists and cosmologists

  7. About TAs Amy Zhang (amy.x.zhang@mail.mcgill.ca) Tianyu Li (tianyu.li@mail.mcgill.ca) I'm a 3rd year PhD student supervised by Doina Precup PhD candidate co-supervised by Joelle Pineau and and Guillaume Rabusseau. My research area is primarily Doina Precup specializing in generalization in on the intersection between tensor methods and reinforcement learning. reinforcement learning. Arna Ghosh (arna.ghosh@mail.mcgill.ca) Haque Ishfaq (haque.ishfaq@mail.mcgill.ca) Second year PhD student supervised by Blake PhD student supervised by Doina, working on Richards working on brain-inspired AI exploration in RL with provable guarantees Arnab Kumar Mondal (arnab.mondal@mail.mcgill.ca) Howard Huang (howard.huang@mail.mcgill.ca) PhD Student supervised by Doina, working on 2nd year PhD student supervised Kaleem Siddiqi hierarchical reinforcement learning Arushi Jain (arushi.jain@mail.mcgill.ca) Samin Yeasar Arnob I am 2nd year Phd supervised by Doina Precup & (samin.arnob@mail.mcgill.ca) Pierre-Luc Bacon. My research area is reinforcement learning and risk-sensitivity. First year Ph.D. student. Research Intereset: Reinforcement learning, Imitation learning COMP 551 | Fall 2020

  8. About this course Understand the theory Practice applying them behind learning algorithms code accompanying (some) lectures lectures programming during the class (?) readings team projects late midterm exam hands on tutorials weekly quizzes late midterm and quizzes (?)

  9. About this course: evaluation to a large extend relies on students' honesty late midterm exam (~20%) date TBD, sometime in November team projects (~60%) by teams of 3 students teams change for every project first project will be posted before add-drop try to pick your team members in the same time zone weekly quizzes (~20%) encourage you to review recently covered topics posted on Mondays, available for 24h a practice quiz one before add-drop

  10. About this course: late submissions All due dates are 11:59 pm Montreal time (EST). No make-up quizzes will be given. We will ignore your worst quiz, so you can miss one quiz without penalty Maximum of five days late for a project 20% penalty for any late submission

  11. About this course: prerequisites Python-Numpy programming skills we start using this from the next lecture we will have a Python-Numpy review tutorial very soon Probability theory you should know random variables, expectations etc. we will have a tutorial to Linear algebra review these two topics matrix product, determinant, null-space of a matrix, span of a set of vectors ... Calculus limit, derivative, integral etc.

  12. About this course: tutorials Python-Numpy ( soon ) Probability theory and linear algebra review ( soon ) Scikit-learn (around the end of September) a Python package for ML We implement many methods in this package from scratch PyTorch Tutorial (around the end of October) a Python package for deep learning COMP 551 | Fall 2020

  13. About this course: outline This is going to change during the semester Part 1: a short tour of ML K-Nearest Neighbours Decision Trees Some Basic Concepts Model selection Curse of dimensionality Dimensionality reduction Maximum likelihood and Bayesian reasoning Multivariate Gaussian Expectation Maximization Naive Bayes

  14. About this course: outline This is going to change during the semester (some topics may be dropped depending on our progress) Part 2: Linear models, probabilistic interpretations and gradient optimization linear regression Nonlinear bases Logistic and softmax regression Gradient descent Part 4: Deep learning Regularization Bias-variance decomposition Multilayer Perceptrons Estimating the uncertainty of predictions* Gradient computation Automated differentiation and Backpropagation Convolutional neural networks Part 3: Kernels and more Frontiers Perceptrons Support Vector Machines Kernel trick * Gaussian process *

  15. About this course: relevant textbooks No required textbook but slides will cover chapters from the following books, available online, which can be used as reference materials. Machine Learning: A Probabilistic Perspective by Kevin Murphy (2012) Pattern Recognition and Machine Learning by Christopher Bishop (2007) Deep Learning (2016) by Ian Goodfellow, Yoshua Bengio, and Aaron Courville The Elements of Statistical Learning : Data Mining, Inference, and Prediction (2009) by Trevor Hastie, Robert Tibshirani and Jerome Friedman COMP 551 | Fall 2020

  16. FAQ Is this the right course for me? prerequisites are very important this course needs lots of time and effort on your side see the course webpage from last year to get an idea there are several other ML courses you should consider (anti-requisite to COMP 551) COMP 451: fundamentals of ML COMP 596: ML for biomedical data ECSE 551: ML for engineers How can I take the class? I'm on the waiting list... if none of the courses above are suitable and you can't take this course next semester, then let me know let's revisit close to the end of add-drop period How can I take the class? I couldn't get on the waiting list... if you have special circumstance that should be treated as an exception please let me know

  17. Code of conduct 0 your answers to quizzes, projects and the exam must be your own work you should not share your solutions with other students Copying (even copying ideas) without giving credit is plagerism you should be respectful in the online course forum and in all other communications you should NOT (re-)post any of the course materials online. This includes: video lectures, codes, and quizzes COMP 551 | Fall 2020

  18. Two pointers 0 Course website https://www.siamak.page/teachings/comp551f20/comp551f20/ MyCourses to check for announcements, form groups for projects, submit weekly quizzes, grades, discussions https://mycourses2.mcgill.ca/d2l/home/432032

  19. Please complete the following poll by Friday (EST) https://forms.gle/852uTec8PVbjZLCbA

  20. your answers so far... your time zone

  21. your answers so far...

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

MACHINE LEARNING Overview 1 1 APPLIED MACHINE LEARNING 2011-2012 APPLIED MACHINE LEARNING

MACHINE LEARNING Overview 1 1 APPLIED MACHINE LEARNING 2011-2012 APPLIED MACHINE LEARNING

APPLIED MACHINE LEARNING 2011-2012 APPLIED MACHINE LEARNING MACHINE LEARNING Overview 1 1 APPLIED MACHINE LEARNING 2011-2012 APPLIED MACHINE LEARNING Exam Format The exam lasts a total of 3 hours: - Upon entering the room, you must

373 views • 21 slides
Applied Machine Learning Introduction 1 APPLIED MACHINE LEARNING Practicalities Contact

Applied Machine Learning Introduction 1 APPLIED MACHINE LEARNING Practicalities Contact

APPLIED MACHINE LEARNING Applied Machine Learning Introduction 1 APPLIED MACHINE LEARNING Practicalities Contact Information of the Instructors APPLIED MACHINE LEARNING Practicalities Slides and exercises will be posted on the website of

1.46k views • 61 slides
APPLIED MACHINE LEARNING Methods for Clustering K-means, Soft K-means DBSCAN 1 MACHINE

APPLIED MACHINE LEARNING Methods for Clustering K-means, Soft K-means DBSCAN 1 MACHINE

MACHINE LEARNING - MSc Course APPLIED MACHINE LEARNING APPLIED MACHINE LEARNING Methods for Clustering K-means, Soft K-means DBSCAN 1 MACHINE LEARNING - MSc Course APPLIED MACHINE LEARNING Objectives Learn basic techniques for data

1.1k views • 74 slides
Introductory Applied Machine Learning The primary aim of the course is to provide the student with

Introductory Applied Machine Learning The primary aim of the course is to provide the student with

Introductory Applied Machine Learning The primary aim of the course is to provide the student with a set of practical tools that can be applied to solve real-world problems in machine learning. Nigel Goddard School of Informatics Machine

716 views • 8 slides
Applied Machine Learning Introduction 1 APPLIED MACHINE LEARNING Practicalities Slides and

Applied Machine Learning Introduction 1 APPLIED MACHINE LEARNING Practicalities Slides and

APPLIED MACHINE LEARNING Applied Machine Learning Introduction 1 APPLIED MACHINE LEARNING Practicalities Slides and exercises will be posted on the website of the class the day before class:

628 views • 37 slides
MACHINE LEARNING Linear and Weighted Regression Support Vector Regression 1 APPLIED MACHINE

MACHINE LEARNING Linear and Weighted Regression Support Vector Regression 1 APPLIED MACHINE

APPLIED MACHINE LEARNING MACHINE LEARNING Linear and Weighted Regression Support Vector Regression 1 APPLIED MACHINE LEARNING Classification (reminder) Maps N -dimensions input x N to discrete values y E.g.: x = [ Length , Color ]

931 views • 68 slides
How Developers Iterate on Machine Learning Workflows -- A Survey of the Applied Machine Learning

How Developers Iterate on Machine Learning Workflows -- A Survey of the Applied Machine Learning

How Developers Iterate on Machine Learning Workflows -- A Survey of the Applied Machine Learning Literature Doris Xin 1 , Litian Ma 1 , Shuchen Song 1 , Rong Ma 2 , Aditya Parameswaran 1 1 University of Illinois at Urbana-Champaign 2 Peking

337 views • 20 slides
APPLIED MACHINE LEARNING Methods for Reduction of Dimensionality through Linear Projection

APPLIED MACHINE LEARNING Methods for Reduction of Dimensionality through Linear Projection

APPLIED MACHINE LEARNING APPLIED MACHINE LEARNING Methods for Reduction of Dimensionality through Linear Projection Principal Component Analysis (PCA) 1 APPLIED MACHINE LEARNING Curse of Dimensionality Computational Costs O(N 2 ) O(N) N:

848 views • 69 slides
APPLIED MACHINE LEARNING Probability Density Functions Gaussian Mixture Models 1 APPLIED

APPLIED MACHINE LEARNING Probability Density Functions Gaussian Mixture Models 1 APPLIED

APPLIED MACHINE LEARNING APPLIED MACHINE LEARNING Probability Density Functions Gaussian Mixture Models 1 APPLIED MACHINE LEARNING Discrete Probabilities Consider two variables x and y taking discrete values over the intervals [1.....N ] and

688 views • 54 slides
Responsible Machine Learning INFO-4604, Applied Machine Learning University of Colorado Boulder

Responsible Machine Learning INFO-4604, Applied Machine Learning University of Colorado Boulder

Responsible Machine Learning INFO-4604, Applied Machine Learning University of Colorado Boulder November 13, 2018 Prof. Michael Paul Is Machine Learning Dangerous? Is Machine Learning Dangerous? Doomsday scenarios not likely any

554 views • 26 slides
Machine Learning Prof. Kuan-Ting Lai 2020/4/11 Applied Math for Machine Learning Linear

Machine Learning Prof. Kuan-Ting Lai 2020/4/11 Applied Math for Machine Learning Linear

Applied Math for Machine Learning Prof. Kuan-Ting Lai 2020/4/11 Applied Math for Machine Learning Linear Algebra Probability Calculus Optimization Linear Algebra Scalar real numbers Vector (1D) Has a magnitude

736 views • 54 slides
Applied Machine Learning Applied Machine Learning Regularization Siamak Ravanbakhsh Siamak

Applied Machine Learning Applied Machine Learning Regularization Siamak Ravanbakhsh Siamak

Applied Machine Learning Applied Machine Learning Regularization Siamak Ravanbakhsh Siamak Ravanbakhsh COMP 551 COMP 551 (winter 2020) (winter 2020) 1 Learning objectives Learning objectives Basic idea of overfitting and underfitting

404 views • 39 slides
Applied Machine Learning Applied Machine Learning Regularization Siamak Ravanbakhsh Siamak

Applied Machine Learning Applied Machine Learning Regularization Siamak Ravanbakhsh Siamak

Applied Machine Learning Applied Machine Learning Regularization Siamak Ravanbakhsh Siamak Ravanbakhsh COMP 551 COMP 551 (winter 2020) (winter 2020) 1 Learning objectives Learning objectives Basic idea of overfitting and underfitting

1.48k views • 135 slides
Applied Machine Learning Applied Machine Learning Convolutional Neural Networks Siamak

Applied Machine Learning Applied Machine Learning Convolutional Neural Networks Siamak

Applied Machine Learning Applied Machine Learning Convolutional Neural Networks Siamak Ravanbakhsh Siamak Ravanbakhsh COMP 551 COMP 551 (winter 2020) (winter 2020) 1 Learning objectives Learning objectives understand the convolution layer

1.34k views • 103 slides
Applied Machine Learning Applied Machine Learning Convolutional Neural Networks Siamak

Applied Machine Learning Applied Machine Learning Convolutional Neural Networks Siamak

Applied Machine Learning Applied Machine Learning Convolutional Neural Networks Siamak Ravanbakhsh Siamak Ravanbakhsh COMP 551 COMP 551 (winter 2020) (winter 2020) 1 Learning objectives Learning objectives understand the convolution layer

609 views • 25 slides
Applied Machine Learning Applied Machine Learning Linear Regression Siamak Ravanbakhsh Siamak

Applied Machine Learning Applied Machine Learning Linear Regression Siamak Ravanbakhsh Siamak

Applied Machine Learning Applied Machine Learning Linear Regression Siamak Ravanbakhsh Siamak Ravanbakhsh COMP 551 COMP 551 (winter 2020) (winter 2020) 1 Learning objectives Learning objectives linear model evaluation criteria how to find

1.22k views • 94 slides
Chatbots for Language Learning Anja Reusch Technische Universit at Dresden Analyse eines

Chatbots for Language Learning Anja Reusch Technische Universit at Dresden Analyse eines

Chatbots for Language Learning Anja Reusch Technische Universit at Dresden Analyse eines Forschungsthemas (INF-D-960) 18.05.2018 1 / 28 Beginner talks to native speaker Beginner has limited knowledge of vocabulary and grammar 2 / 28 3 /

417 views • 28 slides
CS 378: Autonomous Intelligent Robotics (FRI) Dr. Todd Hester Are there any questions?

CS 378: Autonomous Intelligent Robotics (FRI) Dr. Todd Hester Are there any questions?

CS 378: Autonomous Intelligent Robotics (FRI) Dr. Todd Hester Are there any questions? Logistics Progress Reports Due Today Wiki Project Updates Tuesday My job decision New research educator AAAI Spring Symposium

316 views • 9 slides
Sequence-Level Knowledge Distillation Yoon Kim Alexander M. Rush HarvardNLP Code:

Sequence-Level Knowledge Distillation Yoon Kim Alexander M. Rush HarvardNLP Code:

Sequence-Level Knowledge Distillation Yoon Kim Alexander M. Rush HarvardNLP Code: https://github.com/harvardnlp/seq2seq-attn Sequence-to-Sequence Machine Translation (Sutskever et al., 2014; Cho et al., 2014; Bahdanau et al., 2015; Luong et

749 views • 59 slides
Activities of Daily Living Indexing by Hierarchical HMM for Dementia Diagnostics Svebor Karaman,

Activities of Daily Living Indexing by Hierarchical HMM for Dementia Diagnostics Svebor Karaman,

Activities of Daily Living Indexing by Hierarchical HMM for Dementia Diagnostics Svebor Karaman, Jenny Benois-Pineau LaBRI, Rmi Mgret IMS, Yann Gastel, Jean-Francois Dartigues - INSERM U.897, University of Bordeaux Julien

438 views • 25 slides
Communication Lower Bounds for Matrix-Matrix Multiplication Dagstuhl Seminar #15281 July 6-9,

Communication Lower Bounds for Matrix-Matrix Multiplication Dagstuhl Seminar #15281 July 6-9,

Communication Lower Bounds for Matrix-Matrix Multiplication Dagstuhl Seminar #15281 July 6-9, 2015 Julien Langou M OTIVATIONS 2 Motivations Communication Lower Bound for Sequential Matrix-Matrix multiplication Application to Parallel

1.07k views • 95 slides
arXiv:1610.04211v2 [cs.CL] 17 Nov 2016 cult to train and recurrency tends to complex- soning

arXiv:1610.04211v2 [cs.CL] 17 Nov 2016 cult to train and recurrency tends to complex- soning

Gated End-to-End Memory Networks Fei Liu Julien Perez The University of Melbourne Xerox Research Centre Europe Victoria, Australia Grenoble, France fliu3@student.unimelb.edu.au julien.perez@xrce.xerox.com Abstract 1 Introduction

148 views • 10 slides
Bayesian Reinforcement Learning: A Survey Mohammad Ghavamzadeh, Shie Mannor, Joelle Pineau,

Bayesian Reinforcement Learning: A Survey Mohammad Ghavamzadeh, Shie Mannor, Joelle Pineau,

Bayesian Reinforcement Learning: A Survey Mohammad Ghavamzadeh, Shie Mannor, Joelle Pineau, Aviv Tamar Presented by Jacob Nogas ft. Animesh Garg (cameo) Bayesian RL: What - Leverage Bayesian Information in RL problem - Dynamics -

771 views • 52 slides
Video Object Mining : Issues and Perspectives Jonathan Weber, S ebastien Lef` evre, Pierre

Video Object Mining : Issues and Perspectives Jonathan Weber, S ebastien Lef` evre, Pierre

Issues Video Mining Systems Perspectives Conclusion Video Object Mining : Issues and Perspectives Jonathan Weber, S ebastien Lef` evre, Pierre Gan carski LSIIT,University of Strasbourg Ready Business System September 23, 2010

817 views • 71 slides

More recommend