CS480/680 Machine Learning Lecture 1: May 6 th , 2019 Course - - PowerPoint PPT Presentation

▶

Aug 24, 2022 278 likes •528 views

CS480/680 Machine Learning Lecture 1: May 6 th , 2019 Course Introduction Pascal Poupart University of Waterloo CS480/680 Spring 2019 Pascal Poupart 1 Outline Introduction to Machine Learning Course website and logistics University of

SLIDE 1

CS480/680 Machine Learning Lecture 1: May 6th, 2019

Course Introduction Pascal Poupart

CS480/680 Spring 2019 Pascal Poupart 1 University of Waterloo

SLIDE 2

CS480/680 Spring 2019 Pascal Poupart 2

Outline

Introduction to Machine Learning
Course website and logistics

University of Waterloo

SLIDE 3

CS480/680 Spring 2019 Pascal Poupart 3

Instructor

University of Waterloo

Pascal Poupart

15+ years experience in Machine Learning Professor Principal Researcher

SLIDE 4

CS480/680 Spring 2019 Pascal Poupart 4

RBC Borealis AI

Research institute funded by RBC
5 research centers:

– Montreal, Toronto, Waterloo, Edmonton and Vancouver

80 researchers:

– Integrated (applied & fundamental) research model

ML, RL, NLP, computer vision, private AI, fintech
We are hiring!

University of Waterloo

SLIDE 5

CS480/680 Spring 2019 Pascal Poupart 5

Machine Learning

Traditional computer science

– Program computer for every task

New paradigm

– Provide examples to machine – Machine learns to accomplish a task based on the examples

University of Waterloo

SLIDE 6

Definitions

Arthur Samuel (1959): Machine learning is the field
f study that gives computers the ability to learn

without being explicitly programmed.

Tom Mitchell (1998): A computer program is said to

learn from experience E with respect to some class

f tasks T and performance measure P, if its

performance at tasks in T, as measured by P, improves with experience E.

CS480/680 Spring 2019 Pascal Poupart 6 University of Waterloo

SLIDE 7

Three Categories

Supervised learning Reinforcement learning Unsupervised learning

CS480/680 Spring 2019 Pascal Poupart 7 University of Waterloo

SLIDE 8

Supervised Learning

Example: digit recognition (postal code)
Simplest approach:

memorization

CS480/680 Spring 2019 Pascal Poupart 8 University of Waterloo

SLIDE 9

Supervised Learning

Nearest neighbour:

CS480/680 Spring 2019 Pascal Poupart 9 University of Waterloo

SLIDE 10

More Formally

Inductive learning (for supervised learning):

– Given a training set of examples of the form (", $("))

" is the input, $(") is the output

– Return a function ℎ that approximates $

ℎ is called the hypothesis

CS480/680 Spring 2019 Pascal Poupart 10 University of Waterloo

SLIDE 11

Prediction

Find function ℎ that fits " at instances #

CS480/680 Spring 2019 Pascal Poupart 11 University of Waterloo

SLIDE 12

Prediction

Find function ℎ that fits " at instances #

CS480/680 Spring 2019 Pascal Poupart 12 University of Waterloo

SLIDE 13

Prediction

Find function ℎ that fits " at instances #

CS480/680 Spring 2019 Pascal Poupart 13 University of Waterloo

SLIDE 14

Prediction

Find function ℎ that fits " at instances #

CS480/680 Spring 2019 Pascal Poupart 14 University of Waterloo

SLIDE 15

Prediction

Find function ℎ that fits " at instances #

CS480/680 Spring 2019 Pascal Poupart 15 University of Waterloo

SLIDE 16

Generalization

Key: a good hypothesis will generalize well (i.e.

predict unseen examples correctly)

Ockham’s razor: prefer the simplest hypothesis

consistent with data

CS480/680 Spring 2019 Pascal Poupart 16 University of Waterloo

SLIDE 17

ImageNet Classification

1000 classes
1 million images
Deep neural networks

(supervised learning)

CS480/680 Spring 2019 Pascal Poupart 17 University of Waterloo

SLIDE 18

Unsupervised Learning

Output is not given as part of training set
Find model that explains the data

– E.g. clustering, compressed representation, features, generative model

CS480/680 Spring 2019 Pascal Poupart 18 University of Waterloo

SLIDE 19

Unsupervised Feature Generation

Encoder trained on large number of images

CS480/680 Spring 2019 Pascal Poupart 19 University of Waterloo

SLIDE 20

CS480/680 Spring 2019 Pascal Poupart 20

Reinforcement Learning

Agent Environment State Reward Action Goal: Learn to choose actions that maximize rewards

University of Waterloo

SLIDE 21

CS480/680 Spring 2019 Pascal Poupart 21

Animal Psychology

Reinforcements used to train animals
Negative reinforcements:

– Pain and hunger

Positive reinforcements:

– Pleasure and food

Let’s do the same with computers!

– Rewards: numerical signal indicating how good actions are

E.g., game win/loss, money, time, etc.

University of Waterloo

SLIDE 22

CS480/680 Spring 2019 Pascal Poupart 22

Game Playing

Example: Go (one of the oldest

and hardest board games)

Agent: player
Environment: opponent
State: board configuration
Action: next stone location
Reward: +1 win / -1 loose
2016: AlphaGo defeats top player Lee Sedol (4-1)

– Game 2 move 37: AlphaGo plays unexpected move (odds 1/10,000)

University of Waterloo

SLIDE 23

Applications of Machine Learning

Speech recognition

– Siri, Cortana

Natural Language Processing

– Machine translation, question answering, dialog systems

Computer vision

– Image and video analysis

Robotic Control

– Autonomous vehicles

Intelligent assistants

– Activity recognition, recommender systems

Computational finance

– Stock trading, portfolio optimization

CS480/680 Spring 2019 Pascal Poupart 23 University of Waterloo

SLIDE 24

This course

Supervised and unsupervised machine learning
But not reinforcement learning
See CS885 Spring 2018

– Website: https://cs.uwaterloo.ca/~ppoupart/teaching/cs885-spring18/ – Video lectures:

https://www.youtube.com/playlist?list=PLdAoL1zKcqTXFJniO3Tqqn6xMBBL07EDc

CS480/680 Spring 2019 Pascal Poupart 24 University of Waterloo