Machine Learning: Chenhao Tan University of Colorado Boulder - - PowerPoint PPT Presentation

▶
machine learning chenhao tan
SMART_READER_LITE
LIVE PREVIEW

Machine Learning: Chenhao Tan University of Colorado Boulder - - PowerPoint PPT Presentation

Jan 29, 2023 491 likes •939 views

Machine Learning: Chenhao Tan University of Colorado Boulder LECTURE 1 Slides adapted from Jordan Boyd-Graber, Thorsten Joachims Machine Learning: Chenhao Tan | Boulder | 1 of 33 Basic Information Course location and time: ECCS 1B12,

slide-1
SLIDE 1

Machine Learning: Chenhao Tan

University of Colorado Boulder

LECTURE 1 Slides adapted from Jordan Boyd-Graber, Thorsten Joachims

Machine Learning: Chenhao Tan | Boulder | 1 of 33

slide-2
SLIDE 2

Basic Information

  • Course location and time: ECCS 1B12, 17:00-18:15 (MW)
  • Instructor: Chenhao Tan
  • Course assistants: Zhenguo Chen, Tyler Scott
  • Graders: Zhenguo Chen, Sean Harrison

Machine Learning: Chenhao Tan | Boulder | 2 of 33

slide-3
SLIDE 3

Outline of today

  • An overview of machine learning
  • Syllabus
  • Administrivia
  • Pop-up quiz

Machine Learning: Chenhao Tan | Boulder | 3 of 33

slide-4
SLIDE 4

An overview of machine learning

Outline

An overview of machine learning Motivating examples What is machine learning? Why do we want machines to learn? How does machine learning work? Syllabus Administrivia

Machine Learning: Chenhao Tan | Boulder | 4 of 33

slide-5
SLIDE 5

An overview of machine learning | Motivating examples

Machine learning is everywhere!

Machine Learning: Chenhao Tan | Boulder | 5 of 33

slide-6
SLIDE 6

An overview of machine learning | Motivating examples

AlphaGo

Machine Learning: Chenhao Tan | Boulder | 6 of 33

slide-7
SLIDE 7

An overview of machine learning | Motivating examples

Autonomous driving

Machine Learning: Chenhao Tan | Boulder | 7 of 33

slide-8
SLIDE 8

An overview of machine learning | Motivating examples

Movie recommendation

Machine Learning: Chenhao Tan | Boulder | 8 of 33

slide-9
SLIDE 9

An overview of machine learning | Motivating examples

Social networks

Machine Learning: Chenhao Tan | Boulder | 9 of 33

slide-10
SLIDE 10

An overview of machine learning | Motivating examples

Which one will be retweeted more?

Machine Learning: Chenhao Tan | Boulder | 10 of 33

slide-11
SLIDE 11

An overview of machine learning | Motivating examples

Which one will be retweeted more?

Machine Learning: Chenhao Tan | Boulder | 11 of 33

slide-12
SLIDE 12

An overview of machine learning | Motivating examples

Finance

Machine Learning: Chenhao Tan | Boulder | 12 of 33

slide-13
SLIDE 13

An overview of machine learning | Motivating examples

Health/Diagnosis http://www.newyorker.com/magazine/2017/04/03/ai-versus-md

Machine Learning: Chenhao Tan | Boulder | 13 of 33

slide-14
SLIDE 14

An overview of machine learning | Motivating examples

Machine learning is everywhere!

  • smart city
  • entertainment
  • social
  • finance
  • medical

Machine Learning: Chenhao Tan | Boulder | 14 of 33

slide-15
SLIDE 15

An overview of machine learning | Motivating examples

Machine learning is everywhere!

  • smart city
  • entertainment
  • social
  • finance
  • medical

Email me to introduce yourself, one of your core values, and a machine learning application that you care about.

Machine Learning: Chenhao Tan | Boulder | 14 of 33

slide-16
SLIDE 16

An overview of machine learning | What is machine learning?

What is machine learning?

One definition (Mitchell): A computer program is said to learn from

  • experience E with respect to some class of
  • tasks T and
  • performance measure P,

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

Machine Learning: Chenhao Tan | Boulder | 15 of 33

slide-17
SLIDE 17

An overview of machine learning | What is machine learning?

Let us apply this to classic tasks in machine learning!

Machine Learning: Chenhao Tan | Boulder | 16 of 33

slide-18
SLIDE 18

An overview of machine learning | What is machine learning?

ImageNet/Object recognition

  • T: identifying objects in an image
  • E: tons of images with annotated
  • bjects
  • P: how often the objects are identified

correctly

Machine Learning: Chenhao Tan | Boulder | 17 of 33

slide-19
SLIDE 19

An overview of machine learning | What is machine learning?

Sentiment analysis

Machine Learning: Chenhao Tan | Boulder | 18 of 33

slide-20
SLIDE 20

An overview of machine learning | What is machine learning?

Sentiment analysis

  • T: deciding whether a review is

positive or negative

  • E: reviews with ratings
  • P: how often the sentiment is

predicted correctly

Machine Learning: Chenhao Tan | Boulder | 18 of 33

slide-21
SLIDE 21

An overview of machine learning | What is machine learning?

Movie recommendation

  • T: recommend movies
  • E: movie watching history and movie

ratings

Machine Learning: Chenhao Tan | Boulder | 19 of 33

slide-22
SLIDE 22

An overview of machine learning | What is machine learning?

Movie recommendation

  • T: recommend movies
  • E: movie watching history and movie

ratings

  • P: future rating of users? user active

time on website? user subscription periods?

Machine Learning: Chenhao Tan | Boulder | 19 of 33

slide-23
SLIDE 23

An overview of machine learning | Why do we want machines to learn?

Why do we want machines to learn?

  • Intellectually satisfying!
  • Helping us solve problems.

Machine Learning: Chenhao Tan | Boulder | 20 of 33

slide-24
SLIDE 24

An overview of machine learning | Why do we want machines to learn?

Why do we want machines to learn?

  • Intellectually satisfying!
  • Helping us solve problems.

Automate tasks that we know how to perform Explore tasks that we don’t know how to perform

Machine Learning: Chenhao Tan | Boulder | 20 of 33

slide-25
SLIDE 25

An overview of machine learning | Why do we want machines to learn?

Why do we want machines to learn?

  • Intellectually satisfying!
  • Helping us solve problems.

Automate tasks that we know how to perform

  • Object recognition
  • Driving

Explore tasks that we don’t know how to perform

Machine Learning: Chenhao Tan | Boulder | 20 of 33

slide-26
SLIDE 26

An overview of machine learning | Why do we want machines to learn?

Why do we want machines to learn?

  • Intellectually satisfying!
  • Helping us solve problems.

Automate tasks that we know how to perform

  • Object recognition
  • Driving

Explore tasks that we don’t know how to perform

  • Movie recommendation
  • Newsfeed ranking
  • Predict message popularity

Machine Learning: Chenhao Tan | Boulder | 20 of 33

slide-27
SLIDE 27

An overview of machine learning | Why do we want machines to learn?

Why do we want machines to learn?

  • Intellectually satisfying!
  • Helping us solve problems.

Automate tasks that we know how to perform

  • Object recognition
  • Driving

Explore tasks that we don’t know how to perform

  • Movie recommendation
  • Newsfeed ranking
  • Predict message popularity

What about these?

  • Playing Go
  • Finance
  • Health/diagnosis

Machine Learning: Chenhao Tan | Boulder | 20 of 33

slide-28
SLIDE 28

An overview of machine learning | How does machine learning work?

How does machine learning work as of today?

The focus of this course!

  • 1. Collect or happen upon data (X, experience in the previous definition).
  • 2. Analyze it to find patterns.
  • 3. Use those patterns to performance some task (T).

learning algorithm predictor 4.3 stars

Ikiru (1952) UR Foreign Junebug (2005) R Independent La Cage aux Folles (1979) R Comedy The Life Aquatic with Steve Zissou (2004) R Comedy Lock, Stock and Two Smoking Barrels (1998) R Action & Adventure Lost in Translation (2003) R Drama Love and Death (1975) PG Comedy The Manchurian Candidate (1962) PG-13 Classics Memento (2000) R Thrillers Midnight Cowboy (1969) R Classics

Machine Learning: Chenhao Tan | Boulder | 21 of 33

slide-29
SLIDE 29

An overview of machine learning | How does machine learning work?

This course

We will study algorithms that find and exploit patterns in data.

  • These algorithms draw on ideas from statistics and computer science.
  • Applications include
  • natural science (e.g., genomics, neuroscience)
  • web technology (e.g., Google, NetFlix)
  • finance (e.g., stock prediction)
  • policy (e.g., predicting what intervention X will do)
  • and many others

Machine Learning: Chenhao Tan | Boulder | 22 of 33

slide-30
SLIDE 30

An overview of machine learning | How does machine learning work?

This course

We will study algorithms that find and exploit patterns in data.

  • Goal: fluency in thinking about modern machine learning problems.
  • We will learn about a suite of tools in modern data analysis.
  • When to use them
  • The assumptions they make about data
  • Their capabilities, and their limitations
  • Theoretical guarantees
  • We will learn a language and process for solving data analysis problems. On

completing the course, you will be able to learn about a new tool, apply it to data, and understand the meaning of the result.

Machine Learning: Chenhao Tan | Boulder | 22 of 33

slide-31
SLIDE 31

An overview of machine learning | How does machine learning work?

Supervised vs. unsupervised methods

Data

X

Labels

Y

  • Supervised methods find patterns in fully observed data and then try to

predict something from partially observed data.

  • For example, in sentiment analysis, after learning something from annotated

reviews, we want to take new reviews and automatically identify sentiments.

Machine Learning: Chenhao Tan | Boulder | 23 of 33

slide-32
SLIDE 32

An overview of machine learning | How does machine learning work?

Supervised vs. unsupervised methods

Data

X

Hidden Structure

Z

  • Unsupervised methods find hidden structure in data, structure that we can

never formally observe.

  • For example, modeling topics from a collection of scientific papers; evaluation is

usually more difficult.

Machine Learning: Chenhao Tan | Boulder | 24 of 33

slide-33
SLIDE 33

Syllabus

Outline

An overview of machine learning Motivating examples What is machine learning? Why do we want machines to learn? How does machine learning work? Syllabus Administrivia

Machine Learning: Chenhao Tan | Boulder | 25 of 33

slide-34
SLIDE 34

Syllabus

Preliminary schedule

  • Supervised learning
  • Learning theory
  • Unsupervised learning
  • Others
  • Hidden Markov Models (structured prediction)
  • Online learning
  • Reinforcement learning
  • Machine learning and society, interpretability
  • https://chenhaot.com/courses/csci5622/2017fa/syllabus.html,

there is a quiz about syllabus in homework 1.

Machine Learning: Chenhao Tan | Boulder | 26 of 33

slide-35
SLIDE 35

Syllabus

Prerequisites

  • Programming language: Python
  • Math background:
  • probability
  • linear algebra
  • calculus
  • information theory
  • optimization

Machine Learning: Chenhao Tan | Boulder | 27 of 33

slide-36
SLIDE 36

Syllabus

Course text books

  • We will provide reading materials,

mostly from the book.

  • Slightly different focus: same

concepts, use book as starting point

Machine Learning: Chenhao Tan | Boulder | 28 of 33

slide-37
SLIDE 37

Syllabus

Course text books

  • We will provide reading materials,

mostly from the book.

  • Slightly different focus: same

concepts, use book as starting point

Machine Learning: Chenhao Tan | Boulder | 28 of 33

slide-38
SLIDE 38

Syllabus

Course text books

  • We will provide reading materials,

mostly from the book.

  • Slightly different focus: same

concepts, use book as starting point

Machine Learning: Chenhao Tan | Boulder | 28 of 33

slide-39
SLIDE 39

Syllabus

Course text books

  • We will provide reading materials,

mostly from the book.

  • Slightly different focus: same

concepts, use book as starting point

  • Learnability will be from suggested

book

Machine Learning: Chenhao Tan | Boulder | 28 of 33

slide-40
SLIDE 40

Administrivia

Outline

An overview of machine learning Motivating examples What is machine learning? Why do we want machines to learn? How does machine learning work? Syllabus Administrivia

Machine Learning: Chenhao Tan | Boulder | 29 of 33

slide-41
SLIDE 41

Administrivia

Contact information

  • Course webpage:

https://chenhaot.com/courses/csci5622/2017fa/home.html

  • Piazza: https://piazza.com/colorado/fall2017/csci5622/home

Machine Learning: Chenhao Tan | Boulder | 30 of 33

slide-42
SLIDE 42

Administrivia

Grading policy

  • Homeworks: No late submissions (40%)
  • Midterm: in class (15%)
  • Final project (40%)
  • Participation (5%)

Machine Learning: Chenhao Tan | Boulder | 31 of 33

slide-43
SLIDE 43

Administrivia

Final project

  • Project brainstorming: Aug 28 – starting from the first day, getting yourself in

ML mode

  • Group formation due: Oct 4
  • Final project proposal due: Oct 17
  • Final project peer feedback due: Oct 25
  • Midpoint spotlight: Nov 15
  • Midpoint peer feedback due: Nov 27
  • Final project poster session: Dec 13
  • Final project report due: Dec 15

Machine Learning: Chenhao Tan | Boulder | 32 of 33

slide-44
SLIDE 44

Administrivia

Feedback

  • Private emails
  • Periodic survey

Machine Learning: Chenhao Tan | Boulder | 33 of 33