Introduction to Machine Learning Algorithms. 2 What is Artificial Intelligence (AI)? Design and study of computer programs that behave intelligently.

Introduction toIntroduction toMachine Learning AlgorithmsMachine Learning Algorithms

2

What is Artificial Intelligence (AI)?What is Artificial Intelligence (AI)?

Design and study of computer programs that behave intelligently.

Designing computer programs to make computers smarter.

Study of how to make computers do things at which, at the moment, people are better.

3

Research Areas and ApproachesResearch Areas and Approaches

ArtificialIntelligence

Research

Rationalism (Logical)Empiricism (Statistical)Connectionism (Neural)Evolutionary (Genetic)Biological (Molecular)

Paradigm

Application

Intelligent AgentsInformation RetrievalElectronic CommerceData MiningBioinformaticsNatural Language Proc.Expert Systems

Learning AlgorithmsInference MechanismsKnowledge RepresentationIntelligent System Architecture

4

Concept of Machine LearningConcept of Machine Learning

5

6

InformationTheory

ContextContext

ComputerScience

(AI)

CognitiveScience

Statistics

MachineLearning

7

Why Machine Learning?Why Machine Learning?

Recent progress in algorithms and theory Growing flood of online data Computational power is available Budding industry

Three niches for machine learning Data mining: using historical data to improve decisions

Medical records --> medical knowledge Software applications we can’t program by hand

Autonomous driving Speech recognition

Self-customizing programs Newsreader that learns user interests

8

Learning: DefinitionLearning: Definition

Definition Learning is the improvement of performance in some

environment through the acquisition of knowledge resulting from experience in that environment.

the improvementof behavior

the improvementof behavior

on someperformance task

on someperformance task

through acquisitionof knowledge

through acquisitionof knowledge

based on partial task experience

based on partial task experience

9

A Learning Problem: A Learning Problem: EnjoySportEnjoySport

Sky

What is the general concept?

Temp Humid Wind WaterForecast EnjoySports

Sunny Warm Normal Strong Warm Same Yes

Sunny Warm High Strong Warm Same Yes Rainy Cold High Strong Warm Change No

Sunny Warm High Strong Cool Change Yes

10

Metaphors and MethodsMetaphors and Methods

Neurobiology

BiologicalEvolution

HeuristicSearch

StatisticalInference

Memory andRetrieval

ConnectionistLearning

Genetic Learning Tree / RuleInduction

Case-BasedLearning

ProbabilisticInduction

11

What is the Learning Problem?What is the Learning Problem?

Learning = improving with experience at some task Improve over task T, With respect to performance measure P, Based on experience E.

E.g., Learn to play checkers T: Play checkers P: % of games won in world tournament E: opportunity to play against self

12

Machine Learning: TasksMachine Learning: Tasks

Supervised Learning Estimate an unknown mapping from known input- output pairs Learn fw from training set D={(x,y)} s.t.

Classification: y is discrete Regression: y is continuous

Unsupervised Learning Only input values are provided Learn fw from D={(x)} s.t.

Compression Clustering

Reinforcement Learning

)()( xxw fyf

xxw )(f

13

Machine Learning: StrategiesMachine Learning: Strategies

Rote learning Concept learning Learning from examples Learning by instruction Inductive learning Deductive learning Explanation-based learning (EBL) Learning by analogy Learning by observation

14

Supervised LearningSupervised Learning

Given a sequence of input/output pairs of the form <xi, yi>, where xi is a possible input and yi is the output associated with xi.

Learn a function f that accounts for the examples seen so far, f(xi) = yi for all i, and that makes a good guess for the outputs of the inputs that it has not seen.

15

Examples of Input-Output PairsExamples of Input-Output Pairs

Task Inputs Outputs

Recognition

Action

Janitor robot

problem

Descriptions of

objects

Classes that the

objects belong to

Actions or predictionsDescriptions of

situations

Descriptions of

offices (floor, prof’s office)

Yes or No (indicating

whether or not the

office contains a

recycling bin)

16

Unsupervised LearningUnsupervised Learning

Clustering A clustering algorithm partitions the inputs into a fixed

number of subsets or clusters so that inputs in the same cluster are close to one another.

Discovery learning The objective is to uncover new relations in the data.

17

Online and Batch LearningOnline and Batch Learning

Batch methods Process large sets of examples all at once.

Online (incremental) methods Process examples one at a time.

18

Machine Learning Algorithms and Machine Learning Algorithms and ApplicationsApplications

19

Machine Learning AlgorithmsMachine Learning Algorithms

Neural Learning Multilayer Perceptrons (MLPs) Self-Organizing Maps (SOMs)

Evolutionary Learning Genetic Algorithms

Probabilistic Learning Bayesian Networks (BNs)

Other Machine Learning Methods Decision Trees (DTs)

20

Neural Nets for Handwritten Digit Neural Nets for Handwritten Digit RecognitionRecognition

…

Pre-processing

…

…

…

… Input units

Hidden units

Output units0 1 2 3 9

…

Training Test

…

…

…

0 1 2 3 9

?

…

21

ALVINN System: ALVINN System: Neural Network Learning to Steer Neural Network Learning to Steer

an Autonomous Vehiclean Autonomous Vehicle

22

Learning to Navigate a Vehicle by Learning to Navigate a Vehicle by Observing an Human Expert (1/2)Observing an Human Expert (1/2)Inputs

The images produces by a camera mounted on the vehicle

Outputs The actions taken by the human driver to steer

the vehicle or adjust its speed.

Result of learning A function mapping images to control actions

23

Learning to Navigate a Vehicle by Learning to Navigate a Vehicle by Observing an Human Expert (2/2)Observing an Human Expert (2/2)

24

Data Recorrection by a Hopfield NetData Recorrection by a Hopfield Networkwork

original target data

corrupted input data

Recorrected data after

10 iterations

Recorrected data after

20 iterations

Fullyrecorrected data after

35 iterations

25

ANN for Face Recognition

960 x 3 x 4 network is trained on gray-level images of faces to predict whether a person is looking to their left, right, ahead, or up.

26

Data MiningData Mining

-- -- ---- -- ---- -- --

-- -- ---- -- ---- -- --

Target data

Cleaned data

Transformed data

Patterns/ model

KnowledgeDatabase/data warehouse

Selection& Sampling

Selection& Sampling

Preprocessing& Cleaning

Preprocessing& Cleaning

Transformation& reduction

Transformation& reduction

Interpretation/Evaluation

Interpretation/EvaluationData MiningData Mining

Performance system

27

Hot Water Flashing Nozzle with Hot Water Flashing Nozzle with Evolutionary AlgorithmsEvolutionary Algorithms

Start

Hot water entering Steam and droplet at exit

At throat: Mach 1 and onset of flashing

Hans-Paul Schwefel performed the original experiments

28

Machine Learning Applications in Machine Learning Applications in BioinformaticsBioinformatics

29

Bayesian NetworksBayesian Networksfor Gene Expression Analysisfor Gene Expression Analysis

Processed

dataData

Preprocessing

Learningalgorithm

Gene C Gene B

Gene A

Target

Gene D

Gene C Gene B

Gene A

Target

Gene D

Gene C Gene B

Gene A

Target

Gene D

Gene C Gene B

Gene A

Target

Gene D

The values of Gene C and Gene B are given.

Belief propagation Probability for the target is computed.

Learning

Inference

30

Multilayer Perceptrons for Gene Multilayer Perceptrons for Gene Finding and PredictionFinding and Prediction

Coding potential valueCoding potential value

GC CompositionGC Composition

LengthLength

DonorDonor

AcceptorAcceptor

Intron vocabularyIntron vocabulary

basesDiscrete

exon score

0

1

sequence

score

31

Self-Organizing Maps for DNA MiSelf-Organizing Maps for DNA Microarray Data Analysiscroarray Data Analysis

Two-dimensional arrayof postsynaptic neurons

Bundle of synapticconnections

Winning neurons

Input

32

Biological Information ExtractionBiological Information ExtractionText Data

DB

LocationDate

DB Record

Database TemplateFilling

Data Analysis &Field Identification

Data Classification &Field Extraction

Information Extraction

Field PropertyIdentification & Learning

33

Biomolecular ComputingBiomolecular Computing

011001101010001 ATGCTCGAAGCT