COMP 135 Introduction to Machine Learning Prof. Michael C. Hughes - - PowerPoint PPT Presentation

▶
comp 135
SMART_READER_LITE
LIVE PREVIEW

COMP 135 Introduction to Machine Learning Prof. Michael C. Hughes - - PowerPoint PPT Presentation

Jul 08, 2023 308 likes •597 views

COMP 135 Introduction to Machine Learning Prof. Michael C. Hughes (Mike) Fall 2020, First day of class As you join, please check out: * Website: https://www.cs.tufts.edu/comp/135/2020f/ Read syllabus, skim schedule, waitlist info, etc. *

slide-1
SLIDE 1

COMP 135

Introduction to Machine Learning

  • Prof. Michael C. Hughes (“Mike”)

Fall 2020, First day of class

1

As you join, please check out: * Website: https://www.cs.tufts.edu/comp/135/2020f/ Read syllabus, skim schedule, waitlist info, etc. * Piazza forum: https://www.piazza.com/tufts/fall2020/comp135 Access code (today only): validation2020 Ask LIVE questions throughout today’s class (and every class)

Many slides attributable to: Emily Fox (UW), Finale Doshi-Velez (Harvard), Erik Sudderth (UCI), & Liping Liu (Tufts)

slide-2
SLIDE 2

Today’s Agenda

  • Why take this course?
  • What is Machine Learning?
  • What skills/concepts will we learn?
  • Who is teaching?
  • How will we spend our time?

2

Mike Hughes - Tufts COMP 135 - Fall 2020

slide-3
SLIDE 3

3

Mike Hughes - Tufts COMP 135 - Spring 2019

Q: Why should you take this course? A: Machine Learning is everywhere! Those who know how to wield it effectively and responsibly can change the world.

slide-4
SLIDE 4

4

Mike Hughes - Tufts COMP 135 - Fall 2020 Image Credit: Emily Fox

slide-5
SLIDE 5

Goals of this course

Our goal is to prepare students to effectively apply machine learning methods to problems that might arise in "the real world" -- in industry, medicine, government, education, and beyond. Gain skills and understanding for a future as:

  • Developer using ML “out-of-the-box”
  • ML methods researcher

5

Mike Hughes - Tufts COMP 135 – Fall 2020

slide-6
SLIDE 6

After taking this course, you will be able to:

  • Think systematically and ethically
  • Compare/contrast each method’s strengths & limitations
  • "Can ML solve this problem?”
  • “Should ML solve this problem?”
  • Deploy and debug rapidly on real problems
  • Hands-on experience with open-source libraries
  • Address issues in “real-world” data analysis
  • Numerical issues, convergence issues, class imbalance, missing values, etc.
  • Evaluate carefully and honestly
  • Design experiments to assess generalization to never-before-seen data
  • Select task-appropriate performance metrics
  • Report confidence or uncertainty in performance numbers
  • Communicate insightfully and reproducibly
  • Surface key insights via figures, tables, and text in a written report
  • Provide details for a peer to repeat your analysis and draw same conclusions

6

Mike Hughes - Tufts COMP 135 - Fall 2020

slide-7
SLIDE 7

Q: What is Machine Learning?

7

Mike Hughes - Tufts COMP 135 - Fall 2020

slide-8
SLIDE 8

Venn Diagram of Knowledge

8

Mike Hughes - Tufts COMP 135 - Fall 2020

Artificial Intelligence (AI) Data Science Machine Learning (ML) =

Deep Learning

Statistics

slide-9
SLIDE 9

Artificial Intelligence (AI)

Study of “intelligent” systems, with many parts:

logic, planning, search, probabilistic reasoning, learning from experience, interacting with other agents, etc.

9

Mike Hughes - Tufts COMP 135 - Fall 2020 Alpha Go Computer that can beat best human players

  • f the game of “Go” (harder than chess)

DARPA Grand Challenge Autonomous vehicles can navigate a real-world course without humans at the wheel

slide-10
SLIDE 10

Machine Learning (ML)

Study of computer programs that learn from experience/data to perform a task

  • Output: a prediction, decision, or summary

10

Mike Hughes - Tufts COMP 135 - Fall 2020 Face Detection Predict location of human faces in natural images Movie Recommendation Predict what to watch next

slide-11
SLIDE 11

The Machine Learning Process

11

Mike Hughes - Tufts COMP 135 - Fall 2020

Past data (or “experience”) Performance measure Task / Goal input data (now) prediction / decision (now)

slide-12
SLIDE 12

12

Mike Hughes - Tufts COMP 135 - Fall 2020

Q: What concepts will we learn?

slide-13
SLIDE 13

What will we learn?

13

Mike Hughes - Tufts COMP 135 - Fall 2020

Supervised Learning Unsupervised Learning Reinforcement Learning

Data, Label Pairs Performance measure Task data x label y

{xn, yn}N

n=1

slide-14
SLIDE 14

Task: Regression

14

Mike Hughes - Tufts COMP 135 - Fall 2020

Supervised Learning Unsupervised Learning Reinforcement Learning

regression

x y y

is a continuous variable e.g. sales in $$

slide-15
SLIDE 15

Regression Example: Uber

15

Mike Hughes - Tufts COMP 135 - Fall 2020

Supervised Learning Unsupervised Learning Reinforcement Learning

regression

slide-16
SLIDE 16

Regression Example: Uber

16

Mike Hughes - Tufts COMP 135 - Fall 2020

slide-17
SLIDE 17

Regression Example: Uber

17

Mike Hughes - Tufts COMP 135 - Fall 2020

slide-18
SLIDE 18

Task: Classification

18

Mike Hughes - Tufts COMP 135 - Fall 2020

Supervised Learning Unsupervised Learning Reinforcement Learning

classification

y

x2 x1

is a discrete variable (red or blue)

slide-19
SLIDE 19

Classification Example: Swype

19

Mike Hughes - Tufts COMP 135 - Fall 2020

slide-20
SLIDE 20

What will we learn?

20

Mike Hughes - Tufts COMP 135 - Fall 2020

Supervised Learning Unsupervised Learning Reinforcement Learning

Data, Label Pairs Performance measure Task data x label y

{xn, yn}N

n=1

slide-21
SLIDE 21

What will we learn?

21

Mike Hughes - Tufts COMP 135 - Fall 2020

Data Examples data x

Supervised Learning Unsupervised Learning Reinforcement Learning

{xn}N

n=1

Task summary

  • f x

Performance measure

slide-22
SLIDE 22

Task: Embedding

22

Mike Hughes - Tufts COMP 135 - Fall 2020

Supervised Learning Unsupervised Learning Reinforcement Learning

embedding

x2 x1

slide-23
SLIDE 23

Example: Genes vs. geography

23

Mike Hughes - Tufts COMP 135 - Fall 2020

slide-24
SLIDE 24

Task: Recommendation

24

Mike Hughes - Tufts COMP 135 - Fall 2020

Supervised Learning Unsupervised Learning Reinforcement Learning

recommendation

slide-25
SLIDE 25

Recommendation Example

25

Mike Hughes - Tufts COMP 135 - Fall 2020

slide-26
SLIDE 26

Histories of states, actions, rewards Task Next action a Performance measure

What will we learn?

26

Mike Hughes - Tufts COMP 135 - Fall 2020

Supervised Learning Unsupervised Learning Reinforcement Learning

{st, at, rt, st+1, . . .}N

n=1

Recent history

slide-27
SLIDE 27

RL example: Pancake robot

27

Mike Hughes - Tufts COMP 135 – Fall 2020

slide-28
SLIDE 28

What won’t we cover?

  • Clustering
  • Probabilistic models
  • Graphical models
  • Active learning
  • Transfer learning
  • Semi-supervised learning
  • Learning theory
  • ….. lots more

28

Mike Hughes - Tufts COMP 135 - Fall 2020