chenyuicst'pku'edu'cn - PowerPoint PPT Presentation

1 / 47
About This Presentation
Title:

chenyuicst'pku'edu'cn

Description:

????:http://www.icst.pku.edu.cn/course/mlearning/index.htm. 2. Ch1 Introduction ... ML as a scientific discipline was born in mid-seventies of last century. ... – PowerPoint PPT presentation

Number of Views:63
Avg rating:3.0/5.0
Slides: 48
Provided by: Che79
Category:

less

Transcript and Presenter's Notes

Title: chenyuicst'pku'edu'cn


1
????
  • ??
  • ??????????????
  • ??????????

2
??????
  • ??????
  • chenyu_at_icst.pku.edu.cn
  • Tel82529680
  • ?????
  • wanghongyan2003_at_163.com
  • ????http//www.icst.pku.edu.cn/course/mlearning/i
    ndex.htm

3
Ch1 Introduction
  • What is machine learning (ML)?
  • Design a learning system an example
  • ML applications
  • Miscellaneous issues

4
Ch1 Introduction
  • What is machine learning (ML)?
  • Design a learning system an example
  • ML applications
  • Miscellaneous issues

5
A Brief History of Machine Learning
  • ML as a scientific discipline was born in
    mid-seventies of last century.
  • The first ML workshop was held in 1980 at CMU,
    with some two dozen participants and photocopied
    preprints.
  • The first ML publication Machine Learning
    started in 1986.

6
Some Early Seminal Works
  • Perceptron model proposed by Rosenblatt (1958),
    so-called connectionist approach, a seminal
    work in neural work.
  • A system that learns to play checkers (Samuel,
    1959 1963)
  • META-DENTRAL program, which generates rules that
    explains mass spectroscopy data used by expert
    system DENTRAL (Buchanan, 1978), an example of
    symbolic learning.

7
What is Machine Learning?
  • The central problem it studies
  • How can we build computer systems that
    automatically improve with experience, and what
    are the laws that govern all learning processes?
  • We state a learning problem as a machine learns
    with respect to (w.r.t.) a particular task T,
    performance metric P, and type of experience E.

8
What is Machine Learning (2)
  • More precisely, a computer program is said to
    learn from experience E, w.r.t. 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.

9
Alternative Views
  • Machine learning as an attempt to automate parts
    of the scientific method (Wikipedia)
  • Scientific method refers to a body of techniques
    for investigating phenomena, acquiring new
    knowledge, or correcting and integrating previous
    knowledge.
  • Machine learning as computational approaches to
    learning

10
Example of Learning Problem
  • Handwriting Recognition
  • Task T recognizing and classifying handwritten
    words within images
  • Performance measure P percent of words correctly
    classified
  • Training experience E a database of handwritten
    words with given classification

11
Place within Computer Science
  • Think about a niche within the space of all
    software applications where ML plays a special
    role
  • Software applications that we cant program by
    hand (too complicated)
  • Self customizing programs

12
Relation with other Disciplines
  • Human and animal learning (Psychology,
    Neuroscience )
  • Biology, economics, control theory (adaptiveness,
    optimization)

Computer Science
Machine Learning
Statistics
13
Ch1 Introduction
  • What is machine learning (ML)?
  • Design a learning system an example
  • ML applications
  • Miscellaneous issues

14
Design a Learning System
  • Consider the example of learning how to play
    checkers
  • T playing checkers
  • P the percent of games it wins in the world
    tournament
  • E?

15
starting position of a checkers game, from
Wikipedia
16
a checkers board state, from http//www.5025488.n
et/bbs/thread-49430-1-1.html
17
Choose the Training Experience
  • Type of feedback provided by training examples
    (to improve P)
  • Direct individual checkers board states plus the
    correct move for each state
  • Indirect move sequences plus final outcome for
    each game
  • Need to assign each move a credit/punish for the
    final outcome

18
Choose the Training Experience
  • Type of feedback provided by training examples
    (to improve P)
  • Direct individual checkers board states plus the
    correct move for each state
  • Indirect move sequences plus final outcome for
    each game
  • Need to assign each move a credit/punish for the
    final outcome

Easy for learning!
19
Choose the Training Experience (2)
  • How much the learner can control training
    examples?
  • Completely rely on a teacher to select board
    states and provide correct move for each state,
  • have complete control over board states and final
    game outcome (indirect feedback), as in the case
    of playing against itself, or
  • propose confusing board states to a teacher and
    ask for correct move.

20
Choose the Training Experience (3)
  • How well the training examples resemble to the
    cases in which the final performance P is
    measured?
  • Theoretical assumption vs. reality
  • Related topics
  • Concept drifting
  • Incremental learning
  • Transfer learning

21
Chose the Training Experience (3)
  • How well the training examples resemble to the
    cases in which the final performance P is
    measured?
  • Theoretical assumption vs. reality
  • Related topics
  • Concept drifting
  • Incremental learning
  • Transfer learning (current research hotspot!)

22
Update Summary
  • A checkers learning problem
  • T playing checkers
  • P the percent of games it wins in the world
    tournament
  • E games played against itself

23
Remaining Issues
  • What knowledge to be learned?
  • How to represent this knowledge?
  • What algorithm used to learn the knowledge
    (learning mechanism)?

24
Remaining Issues
  • What knowledge to be learned?
  • How to represent this knowledge?
  • What algorithm used to learn the knowledge
    (learning mechanism)?

25
Choose the Target Function
  • Think of a checker learning program as an
    optimization problem At every board state the
    program chooses the best move among all the legal
    moves.
  • Reformulate what to be learned as a function
    ChooseMove B ? M, or a better representation, V
    B ? R

real number set
26
How to Define Target Function V?
  • If b is a final board state, then it is simple
  • If b is won, V(b)100 (or other big number)
  • If b is lost, V(b)-100
  • If b is draw, V(b)0

27
How to Define Target Function V ?(2)
  • Otherwise, it is tough! We might define
    V(b)V(b), where b is the best final state
    that can be achieved starting from b and playing
    optimally until end of the program.
  • However, such definition is not operational!

28
Remaining Issues
  • What knowledge to be learned?
  • How to represent this knowledge?
  • What algorithm used to learn the knowledge
    (learning mechanism)?

29
Choose a Representation of V
  • A tradeoff between the expressiveness of V and
    demand for training data
  • Let us consider a simple representation ? of V a
    linear combination of following board states
  • x1 black pieces on the board
  • x2 red pieces
  • x3 black kings
  • x4 red kings
  • x5 black pieces threatened by red (i.e. which
    can be captured on reds next move)
  • x6 red pieces threatened by black (i.e. which
    can be captured on blacks next move)

30
A Simple Representation of V
31
Remaining Issues
  • What knowledge to be learned?
  • How to represent this knowledge?
  • What algorithm used to learn the knowledge
    (learning mechanism)?

32
Choose an Approximation Algorithm
  • Choose a set of training examples (b, Vtrain(b))
  • Estimate Vtrain(b)
  • For some board state, it is obvious, e.g.
    Vtrain(b)100 if x20 (assuming the learning
    program plays black).
  • Only indirect training examples are available.
    One common approach is via iteration, such as
  • Vtrain(b) ??(Successor(b)).

33
Adjust the Weights
  • A common approach to obtain the weights is by
    minimizing the sum of square of error

34
An Algorithm for Finding Weights
  • Least mean square (LMS) weight update rule
  • For each training example (b, Vtrain(b))
  • Use the current weights to calculate ?(b).
  • For each weight wi, update it as

35
Summary of the Whole Design Process
36
Issues in Machine Learning
  • What algorithms exist for learning general target
    functions from training examples? Convergence of
    algorithms given sufficient examples? Which
    algorithms work best for which kind of target
    functions?
  • How does number of examples influence accuracy of
    learned functions? How dose character of
    hypothesis space impact accuracy?
  • How can prior knowledge of learner help?

37
Issues in Machine Learning (2)
  • What specific functions should the learner
    attempt to learn? Can this process be automated?
  • How can the learner automatically alter its
    representation to improve its ability to
    represent and learn the target function?

38
Ch1 Introduction
  • What is machine learning (ML)?
  • Design a learning system an example
  • ML applications
  • Miscellaneous issues

39
Machine Learning
  • Speech Recognition
  • Reinforcement learning
  • Predictive modeling
  • Pattern discovery
  • Hidden Markov models
  • Convex optimization
  • Explanation-based learning
  • ....
  • Automated Control learning
  • Extracting facts from text

40
Example Self-Learning Robot iCub
  • iCub is a humanoid robot the size of a 3.5 year
    old child. It has been developing for 5-years
    under the project RobotCub, funded by European
    Commission for studying human cognition.
  • RobotCub is an open source project.

41
Application Successes
  • Speech recognition
  • Two training stages speaker-independent and
    speaker-dependent
  • Computer vision
  • Face recognition, sorting letters contain
    hand-written addresses by US postal office
  • Bio-surveillance
  • Detecting and tracking outbreak of disease
  • Robot control
  • Robots drive autonomously

42
Ch1 Introduction
  • What is machine learning (ML)?
  • Design a learning system an example
  • ML applications
  • Miscellaneous issues

43
Research on ML
  • Current research questions
  • Long-term questions
  • For the above two items, see The Discipline
    of Machine Learning by Tom Mitchell for a sample
    of questions.
  • Machine learning for tough problems relevant
    novelty detection, structural learning, active
    learning.

44
Ethical Questions
  • When and where to apply ML technology?
  • For example, when collecting data for security or
    law enforcement, or for marketing purpose, what
    about our privacy?
  • Privacy-preserving data mining. Borrow something
    from Secure Multiparty Computing (SMC)?

45
Major Conference and Journal
  • International Conference on Machine Learning
    (ICML)
  • Conference on Neural Information Processing
    Systems (NIPS)
  • Annual Conference on Learning Theory (COLT)
  • Journal of Machine Learning Research (JMLR)
  • Machine Learning

46
Some Interesting Ref
  • Pattern Recognition in industry, by Phiroz
    Bhagat, Elsevier, 2005.
  • UCI Machine Learning Repository
  • machine learning item on Wikipedia

47
HW
  • Read The Discipline of Machine Learning by Tom
    Mitchell
  • 1.2 (10pt, due Sept 22)
  • Bonus problem pick up one challenge from Jaimes
    paper written in 1992, and write a detailed
    update progress report. (10pt)
Write a Comment
User Comments (0)
About PowerShow.com