Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 Machine Learning 1.Where does machine learning fit in computer science? 2.What is machine learning? 3.Where can machine learning be applied? 4.Should.

Similar presentations


Presentation on theme: "1 Machine Learning 1.Where does machine learning fit in computer science? 2.What is machine learning? 3.Where can machine learning be applied? 4.Should."— Presentation transcript:

1 1 Machine Learning 1.Where does machine learning fit in computer science? 2.What is machine learning? 3.Where can machine learning be applied? 4.Should I care about machine learning at all?

2 2 Where does machine learning fit in computer science? Search Artificial Intelligence Planning Knowledge Representation Machine Learning Robotics Clustering Classification Genetic Algorithms Reinforcement Learning Field of Study

3 3 Where does machine learning fit in computer science? (2) MachineLearning Probability & Statistics ComputationalComplexityTheory InformationTheory Philosophy Neurobiology ArtificialIntelligence Multidisciplinary Field

4 4 Where does machine learning fit in computer science? (3) Selection Target Data Preprocessing Data Preprocessed Data Transformation Transformed Data Patterns Data Mining Interpretation & Evaluation Knowledge Knowledge Discovery and Data Mining

5 5 Machine Learning 1.Where does machine learning fit in computer science? 2.What is machine learning? 3.Where can machine learning be applied? 4.Should I care about machine learning at all?

6 6 Machine 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?

7 7 What is Machine Learning? Definition Machine learning is the study of how to make computers learn or adapt; the goal is to make computers improve their performance through experience. Experience E ComputerLearningAlgorithm Class of Tasks T Performance P

8 8 What is Machine Learning? Definition (2) Experience E ComputerLearningAlgorithm Class of Tasks T Performance P

9 9 What is Machine Learning? Definition (3) It is the kind of activity on which the computer will learn to improve its performance. Examples: Learning to Play chess Recognizing Recognizing Images of HandwrittenWords Diagnosing Diagnosingpatients coming into the hospital hospital Class of Tasks:

10 10 What is Machine Learning? Definition (4) Experience E ComputerLearningAlgorithm Class of Tasks T Performance P

11 11 What is Machine Learning? Definition (5) Experience: What has been recorded in the past Experience: What has been recorded in the past Performance: A measure of the quality of the response or action. Performance: A measure of the quality of the response or action. Example: Handwritten recognition using Neural Networks Experience: a database of handwritten images with their correct classification with their correct classification Performance: Accuracy in classifications Experience and Performance

12 12 What is Machine Learning? Definition (6) Experience E ComputerLearningAlgorithm Class of Tasks T Performance P

13 13 What is Machine Learning? Definition (7) Example: Diagnosing a patient coming into the hospital. Features:  X 1 : Temperature  X 2 : Blood pressure  X 3 : Blood type  X 4 : Age  X 5 : Weight  Etc. Given a new example X = Given a new example X = F(X) = w 1 x 1 + w 2 x 2 + w 3 x 3 = … + w n x n If F(X) > T predict heart disease otherwise predict no heart disease The Representation of the Target Knowledge Designing a Learning System

14 14 Machine 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?

15 15 What is Machine Learning? Types of Machine Learning Supervised Learning Unsupervised Learning Reinforcement Learning Evolutionary Learning

16 16 What is Machine Learning? Types of Machine Learning (2) Supervised 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 regression Two modes: classification and regression Machine learning algorithms abound: Decision Trees Decision Trees Rule-based systems Rule-based systems Neural networks Neural networks Nearest-neighbor Nearest-neighbor Support-Vector Machines Support-Vector Machines Bayesian Methods Bayesian Methods

17 17 What is Machine Learning? Types of Machine Learning (2) Supervised Learning – Neural Networks Artificial Neural Networks are crude attempts to model the highly massive parallel and distributed processing we believe takes place in the brain. Consider: 1)the speed at which the brain recognizes images; 2)the many neurons populating a brain; 3)the speed at which a single neuron transmits signals. Brain Neuron Model Representation

18 18 What is Machine Learning? Types of Machine Learning (2) Supervised Learning – Neural Networks(2) Input nodes Internal nodes Output nodes LeftStraightRight

19 19 What is Machine Learning? Types of Machine Learning (3) Unsupervised 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, 2 nd Ed. Wiley Interscience (2000)

20 20 What is Machine Learning? Types of Machine Learning (4) Reinforcement Learning Supervised Learning: Example Class Reinforcement Learning: Situation Reward …

21 21 What is Machine Learning? Types of Machine Learning (5) Evolutionary Learning Methods inspired by the process of biological evolution. Main ideas Population of solutions Assign a score or fitness value to each solution Retain the best solutions (survival of the fittest) Generate new solutions (offspring)

22 22 Machine 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?

23 23 Where can machine learning be applied? Application 1

24 24 Where can machine learning be applied? Application 1 (2) Automatic Car Drive Class of Tasks: Learning to drive on highways from vision stereos. Knowledge: Images and steering commands recorded while observing a human driver. Performance Module: Accuracy in classification

25 25 Where can machine learning be applied? Application 2 Learning to classify astronomical structures. galaxy stars Features: o Color o Size o Mass o Temperature o Luminosity unkown

26 26 Where can machine learning be applied? Application 2 (2) Classifying Astronomical Objects Class of Tasks: Learning to classify new objects. Knowledge: database of images with correct classification. Performance Module: Accuracy in classification

27 27 Where can machine learning be applied? Other Applications  Bio-Technology  Protein Folding Prediction  Micro-array gene expression  Computer Systems Performance Prediction  Banking Applications  Credit Applications  Fraud Detection  Character Recognition (US Postal Service)  Web Applications  Document Classification  Learning User Preferences

28 28 Machine 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?

29 29 Should I care about Machine Learning at all?  Yes, you should!  Machine learning is becoming increasingly popular and has become a cornerstone in many industrial applications.  Machine learning provides algorithms for data mining, where the goal is to extract useful pieces of information (i.e., patterns) from large databases.  The computer industry is heading towards systems that will be able to adapt and heal themselves automatically.  The electronic game industry is now focusing on games where characters adapt and learn through time.  NASA is interested in robots able to adapt in any environment autonomously.

30 30 Summary 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: class of tasks, performance metric, and body of experience. A learning algorithm needs the following elements: class of tasks, performance metric, and body of experience. The design of a learning algorithm requires to define the knowledge to learn, the representation of the target knowledge, and the learning mechanism. The design of a learning algorithm requires to define the knowledge to learn, the representation of the target knowledge, and the learning mechanism. Machine learning counts with many successful applications and is becoming increasingly important in science and industry. Machine learning counts with many successful applications and is becoming increasingly important in science and industry.


Download ppt "1 Machine Learning 1.Where does machine learning fit in computer science? 2.What is machine learning? 3.Where can machine learning be applied? 4.Should."

Similar presentations


Ads by Google