1 machine learning 1.where does machine learning fit in computer science? 2.what is machine...
TRANSCRIPT
11
Machine LearningMachine Learning
1.1. Where does machine learning fit in computer science?Where does machine learning fit in computer science?
2.2. What is machine learning?What is machine learning?
3.3. Where can machine learning be applied?Where can machine learning be applied?
4.4. Should I care about machine learning at all?Should I care about machine learning at all?
22
Where does machine learning fit in computer Where does machine learning fit in computer science? science?
Search
Artificial Intelligence
Planning Knowledge
Representation
Machine Learning Robotics
Clustering
Classification
Genetic Algorithms
Reinforcement
Learning
Field of Study
33
Where does machine learning fit in computer Where does machine learning fit in computer science? (2)science? (2)
MachineMachineLearningLearning
Probability &Probability &StatisticsStatistics
ComputationalComputationalComplexityComplexity
TheoryTheory InformationInformationTheoryTheory
PhilosophyPhilosophy
NeurobiologyNeurobiology
ArtificialArtificialIntelligenceIntelligence
Multidisciplinary FieldMultidisciplinary Field
44
Where does machine learning fit in Where does machine learning fit in computer science? (3)computer science? (3)
Selection
Target Data
Preprocessing
Data Preprocessed Data
Transformation
Transformed Data
PatternsData Mining
Interpretation & EvaluationKnowledge
Knowledge Discovery and Data Mining
55
Machine LearningMachine Learning
1.1. Where does machine learning fit in computer science?Where does machine learning fit in computer science?
2.2. What is machine learning?What is machine learning?
3.3. Where can machine learning be applied?Where can machine learning be applied?
4.4. Should I care about machine learning at all?Should I care about machine learning at all?
66
Machine LearningMachine Learning
• Where does machine learning fit in computer science?Where does machine learning fit in computer science?
• What is machine learning?What is machine learning?
• DefinitionDefinition
• Types of Machine LearningTypes of Machine Learning
• Where can machine learning be applied?Where can machine learning be applied?
• Should I care about machine learning at all?Should I care about machine learning at all?
77
What is Machine Learning?What is Machine Learning?DefinitionDefinition
Machine learning is the study of how to make computers Machine learning is the study of how to make computers learn or adapt; the goal is to make computers improve their learn or adapt; the goal is to make computers improve their performance through experience.performance through experience.
Experience Experience EE
ComputerComputer
LearningLearning
AlgorithmAlgorithm
Class of Tasks Class of Tasks TT PerformancePerformance PP
88
What is Machine Learning? What is Machine Learning? Definition (2)Definition (2)
Experience Experience EE
ComputerComputer
LearningLearning
AlgorithmAlgorithm
Class of Tasks Class of Tasks TT PerformancePerformance PP
99
What is Machine Learning? What is Machine Learning? Definition (3)Definition (3)
It is the kind of activity on which the computer will learn to It is the kind of activity on which the computer will learn to improve its performance. Examples: improve its performance. Examples:
Learning to Learning to Play chess Play chess
Recognizing Recognizing Images of Images of
Handwritten Handwritten WordsWords
Diagnosing Diagnosing patientspatients
coming into thecoming into the hospitalhospital
Class of Tasks:Class of Tasks:
1010
What is Machine Learning? What is Machine Learning? Definition (4)Definition (4)
Experience Experience EE
ComputerComputer
LearningLearning
AlgorithmAlgorithm
Class of Tasks Class of Tasks TT PerformancePerformance PP
1111
What is Machine Learning? What is Machine Learning? Definition (5)Definition (5)
ExperienceExperience: What has been recorded in the past: What has been recorded in the past
PerformancePerformance: A measure of the quality of the response or action. : A measure of the quality of the response or action.
Example: Example: Handwritten recognition using Neural NetworksHandwritten recognition using Neural Networks
ExperienceExperience: a database of handwritten images : a database of handwritten images with their correct classification with their correct classification
PerformancePerformance: Accuracy in classifications: Accuracy in classifications
Experience and PerformanceExperience and Performance
1212
What is Machine Learning? What is Machine Learning? Definition (6)Definition (6)
Experience Experience EE
ComputerComputer
LearningLearning
AlgorithmAlgorithm
Class of Tasks Class of Tasks TT PerformancePerformance PP
1313
What is Machine Learning? What is Machine Learning? Definition (7)Definition (7)
Example: Diagnosing a patient coming into the hospital.Example: Diagnosing a patient coming into the hospital.
Features:Features: XX11: Temperature: Temperature XX22: Blood pressure: Blood pressure XX33: Blood type: Blood type XX44: Age: Age XX55: Weight: Weight Etc.Etc.
Given a new example X = < xGiven a new example X = < x11, x, x22, …, x, …, xnn > >
F(X) = wF(X) = w11xx11 + w + w22xx22 + w + w33xx33 = … + w = … + wnnxxnn
If F(X) > T predict If F(X) > T predict heart diseaseheart disease otherwise predict otherwise predict no heart diseaseno heart disease
The Representation of the Target Knowledge
Designing a Learning SystemDesigning a Learning System
1414
Machine LearningMachine Learning
• Where does machine learning fit in computer science?Where does machine learning fit in computer science?
• What is machine learning?What is machine learning?
• DefinitionDefinition
• Types of Machine LearningTypes of Machine Learning
• Where can machine learning be applied?Where can machine learning be applied?
• Should I care about machine learning at all?Should I care about machine learning at all?
1515
What is Machine Learning?What is Machine Learning?Types of Machine LearningTypes of Machine Learning
• Supervised Learning
• Unsupervised Learning
• Reinforcement Learning
• Evolutionary Learning
1616
What is Machine Learning?What is Machine Learning?Types of Machine Learning (2)Types of Machine Learning (2)
Supervised LearningSupervised Learning
Each example or object has a class attached to it.Each example or object has a class attached to it. We try to learn a mapping from examples to classes.We try to learn a mapping from examples to classes.
Two modes: classification and regressionTwo modes: classification and regression
Machine learning algorithms abound:Machine learning algorithms abound: Decision Trees Decision Trees Rule-based systemsRule-based systems Neural networksNeural networks Nearest-neighborNearest-neighbor Support-Vector MachinesSupport-Vector Machines Bayesian MethodsBayesian Methods
1717
What is Machine Learning? What is Machine Learning? Types of Machine Learning (2) Types of Machine Learning (2)
Supervised Learning – Neural NetworksSupervised Learning – Neural Networks
Artificial Neural NetworksArtificial Neural Networks are crude attempts to model the highly massive are crude attempts to model the highly massive parallel and distributed processing we believe takes place in the brain. parallel and distributed processing we believe takes place in the brain.
Consider: Consider: 1)1) the speed at which the brain recognizes images; the speed at which the brain recognizes images; 2)2) the many neurons populating a brain; the many neurons populating a brain; 3)3) the speed at which a single neuron transmits signals. the speed at which a single neuron transmits signals.
Brain
NeuronModel Representation
1818
What is Machine Learning?What is Machine Learning? Types of Machine Learning (2) Types of Machine Learning (2)
Supervised Learning – Neural Networks(2)Supervised Learning – Neural Networks(2)
Input nodesInput nodes
Internal nodesInternal nodes
Output nodesOutput nodes
Left Left StraightStraight RightRight
1919
What is Machine Learning?What is Machine Learning? Types of Machine Learning (3) Types of Machine Learning (3)
Unsupervised LearningUnsupervised Learning
Examples or objects have no class attached to them.Examples or objects have no class attached to them.
From “Pattern Classification” by Duda, Hart and Stork, 2nd Ed. Wiley Interscience (2000)
2020
What is Machine Learning? What is Machine Learning? Types of Machine Learning (4) Types of Machine Learning (4)
Reinforcement LearningReinforcement Learning
Supervised Learning:
Example Class
Reinforcement Learning:
Situation Reward Situation Reward
…
2121
What is Machine Learning?What is Machine Learning? Types of Machine Learning (5) Types of Machine Learning (5)
Evolutionary LearningEvolutionary Learning
Methods inspired by the process of biological evolution.
Main ideas
Population of solutions
Assign a score orfitness value to each solution
Retain the bestsolutions (survival of the fittest)
Generate newsolutions (offspring)
2222
Machine LearningMachine Learning
• Where does machine learning fit in computer science?Where does machine learning fit in computer science?
• What is machine learning?What is machine learning?
• Where can machine learning be applied?Where can machine learning be applied?
• Should I care about machine learning at all?Should I care about machine learning at all?
2323
Where can machine learning be applied?Where can machine learning be applied?Application 1Application 1
Automatic car drive (ALVINN 1989)
Train computer-controlled vehicle to steer correctly when
driving on a variety of road types.
computer
(learning algorithm)
class 1
steer to the left
class 2
steer to the right
class 3
continue straight
2424
Where can machine learning be applied? Where can machine learning be applied? Application 1 (2)Application 1 (2)
Automatic Car DriveAutomatic Car Drive
Class of TasksClass of Tasks: : Learning to drive on highways from Learning to drive on highways from
vision stereos.vision stereos.
KnowledgeKnowledge: : Images and steering commands recorded Images and steering commands recorded while observing a human driver.while observing a human driver.
Performance ModulePerformance Module: Accuracy in classification : Accuracy in classification
2525
Where can machine learning be applied? Where can machine learning be applied? Application 2Application 2
Learning to classify astronomical structures.Learning to classify astronomical structures.
galaxygalaxy
starsstars
Features:Features:o ColorColoro SizeSizeo MassMasso TemperatureTemperatureo LuminosityLuminosity
unkownunkown
2626
Where can machine learning be applied? Where can machine learning be applied? Application 2 (2)Application 2 (2)
Classifying Astronomical ObjectsClassifying Astronomical Objects
Class of TasksClass of Tasks: : Learning to classify new objects.Learning to classify new objects.
KnowledgeKnowledge: : database of images with correct database of images with correct classification.classification.
Performance ModulePerformance Module: Accuracy in classification : Accuracy in classification
2727
Where can machine learning be applied? Where can machine learning be applied? Other Applications Other Applications
Bio-TechnologyBio-Technology Protein Folding Prediction Protein Folding Prediction Micro-array gene expressionMicro-array gene expression
Computer Systems Performance PredictionComputer Systems Performance Prediction Banking ApplicationsBanking Applications
Credit ApplicationsCredit Applications Fraud DetectionFraud Detection
Character Recognition (US Postal Service)Character Recognition (US Postal Service) Web ApplicationsWeb Applications
Document ClassificationDocument Classification Learning User PreferencesLearning User Preferences
2828
Machine LearningMachine Learning
• Where does machine learning fit in computer science?Where does machine learning fit in computer science?
• What is machine learning?What is machine learning?
• Where can machine learning be applied?Where can machine learning be applied?
• Should I care about machine learning at all?Should I care about machine learning at all?
2929
Should I care about Machine Learning at all?Should I care about Machine Learning at all?
Yes, you should!Yes, you should!
Machine learning is becoming increasingly popular and has become a Machine learning is becoming increasingly popular and has become a cornerstone in many industrial applications.cornerstone in many industrial applications.
Machine learning provides algorithms for data mining, where the goal Machine learning provides algorithms for data mining, where the goal is to extract useful pieces of information (i.e., patterns) from large is to extract useful pieces of information (i.e., patterns) from large databases. databases.
The computer industry is heading towards systems that will be able to The computer industry is heading towards systems that will be able to adapt and heal themselves automatically. adapt and heal themselves automatically.
The electronic game industry is now focusing on games where The electronic game industry is now focusing on games where characters adapt and learn through time.characters adapt and learn through time.
NASA is interested in robots able to adapt in any environment NASA is interested in robots able to adapt in any environment autonomously.autonomously.
3030
SummarySummary
Machine learning is the study of how to make computers learn.Machine learning is the study of how to make computers learn.
A learning algorithm needs the following elements: A learning algorithm needs the following elements: class of tasks, class of tasks, performance metric, and body of experience. performance metric, and body of experience.
The design of a learning algorithm requires to define the The design of a learning algorithm requires to define the knowledge to knowledge to learn, the representation of the target knowledge, and the learning learn, the representation of the target knowledge, and the learning mechanism.mechanism.
Machine learning counts with many successful applications and is Machine learning counts with many successful applications and is becoming increasingly important in science and industry.becoming increasingly important in science and industry.