learning from observations inductive learning - learning from examples machine learning

Learning from observations

Inductive Learning - learning from examples

Machine Learning

2

What Is Machine Learning?“Logic is not the end of wisdom, it is just the beginning” --- Spock

System

Knowledge

Environment

Action1

time

Knowledge

Environment

System

changed

same

Action2

3

Learning & Adaptation

• ”Modification of a behavioral tendency by expertise.” (Webster 1984)

• ”A learning machine, broadly defined is any device whose actions are influenced by past experiences.” (Nilsson 1965)

• ”Any change in a system that allows it to perform better the second time on repetition of the same task or on another task drawn from the same population.” (Simon 1983)

• ”An improvement in information processing ability that results from information processing activity.” (Tanimoto 1990)

4

Ways humans learn things …talking, walking, running… Learning by mimicking, reading or being told facts Tutoring Being informed when one is correct Experience Feedback from the environment Analogy Comparing certain features of existing knowledge

to new problems Self-reflection Thinking things in ones own mind, deduction,

discovery

5

6

7

A few achievements

Programs that can: Recognize spoken words Predict recovery rates of pneumonia

patients Detect fraudulent use of credit cards Drive autonomous vehicles Play games like backgammon –

approaching the human champion!

8

Machine Learning

Machine learning involves automatic procedures that learn a task from a series of examples

Most convenient source of examples is data

9

Learning

Definition: 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.

10

Machine Learning Models Classification Clustering Regression Time series analysis Association Analysis Sequence Discovery ….

11

ClassificationAssign items to one of a set of predefined classes of objects based on a set of observed features

Text

12

ClassificationAssign items to one of a set of predefined classes of objects based on a set of observed features

13

ClusteringSeeks to place objects into meaningful groups automatically, based on their similarity. Does not require the groups to be predefined. The hope in applying clustering algorithms is that they will discover useful but unknown classes of items.

14

Classification example

Model

Test setTrain set

Learning system

New data

LoanYes/No

15

Inductive learning Simplest form: learn a function from examples

f is the target function

An example is a pair (x, f(x))

Problem: find a hypothesis hsuch that h ≈ fgiven a training set of examples

16

Inductive learning method Construct/adjust h to agree with f on training set (h is consistent if it agrees with f on all examples) E.g., curve fitting:

17

Inductive learning method Construct/adjust h to agree with f on training set (h is consistent if it agrees with f on all examples) E.g., curve fitting:

18

Inductive learning method Construct/adjust h to agree with f on training set (h is consistent if it agrees with f on all examples) E.g., curve fitting:

19

Inductive learning method Construct/adjust h to agree with f on training set (h is consistent if it agrees with f on all examples) E.g., curve fitting:

20

Inductive learning method Construct/adjust h to agree with f on training set (h is consistent if it agrees with f on all examples) E.g., curve fitting:

21

Inductive learning method Construct/adjust h to agree with f on training set (h is consistent if it agrees with f on all examples) E.g., curve fitting:

Ockham’s razor: prefer the simplest hypothesis consistent with data

22

Machine Learning Methods Instance Based Methods (CBR, k-NN) Decision Trees Artificial Neural Networks Bayesian Networks Naïve Base Evolutionary Strategies Support Vector Machines ..

23

Classification example

Weight

Heighto

xx

xx

xx

xx x

x

xo

ooo

o oo

oo

x

oox

x

x - weight-lifters

o - ballet dancers

Features: height, weight

24

Classification example - Simple Model

Weight

Heighto

xx

xx

xx

xx x

x

xo

ooo

o oo

oo

x

oox

x

x - weight-lifters

o - ballet dancers

Decision boundaryDecision boundary

Features: height, weight

25

Classification example - Complex model

Weight

Heighto

xx

xx

xx

xx x

x

xo

ooo

o oo

oo

x

oox

x

x - weight-lifters

o - ballet dancers

Complex Decision boundaryComplex Decision boundary

Features: height, weight

Note: A simple decision boundary is better than a Note: A simple decision boundary is better than a complex one - It GENERALIZES better.complex one - It GENERALIZES better.

26

Learning Paradigms

Supervised learning - with teacher inputs and correct outputs are provided by the teacher

Reinforced learning - with reward or punishment an action is evaluated

Unsupervised learning - with no teacher no hint about correct output is given

27

Nearest Neighbor Simple effective approach for supervised

learning problems

Envision each example as a point in n-dimensional space- Picture with 2 of them

Classify test point same as nearest training point (Euclidean distance)

Patient ID # of Tumors Avg Area Avg Density Diagnosis1 5 20 118 Malignant2 3 15 130 Benign3 7 10 52 Benign4 2 30 100 Malignant

28

k-Nearest Neighbor Nearest Neighbor can be subject to

noise Incorrectly classified training points Training anomalies

k-Nearest Neighbor Find k nearest training points (k odd)

and vote on which classification

Works on numerical data