Neural Networks and Their Applications John Paxton Montana State University August 14, 2003.

Slides:



Advertisements
Similar presentations
NEURAL NETWORKS Biological analogy
Advertisements

Computer Science Department FMIPA IPB 2003 Neural Computing Yeni Herdiyeni Computer Science Dept. FMIPA IPB.
Machine Learning: Connectionist McCulloch-Pitts Neuron Perceptrons Multilayer Networks Support Vector Machines Feedback Networks Hopfield Networks.
Machine Learning Neural Networks
1 Neural Networks - Basics Artificial Neural Networks - Basics Uwe Lämmel Business School Institute of Business Informatics
Artificial Intelligence (CS 461D)
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Neural Networks. R & G Chapter Feed-Forward Neural Networks otherwise known as The Multi-layer Perceptron or The Back-Propagation Neural Network.
AN INTERACTIVE TOOL FOR THE STOCK MARKET RESEARCH USING RECURSIVE NEURAL NETWORKS Master Thesis Michal Trna
Neural Networks in Electrical Engineering Prof. Howard Silver School of Computer Sciences and Engineering Fairleigh Dickinson University Teaneck, New Jersey.
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
JYC: CSM17 Bioinformatics Week 9: Simulations #3: Neural Networks biological neurons natural neural networks artificial neural networks applications.
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
Traffic Sign Recognition Using Artificial Neural Network Radi Bekker
CSC 4510 – Machine Learning Dr. Mary-Angela Papalaskari Department of Computing Sciences Villanova University Course website:
Artificial neural networks:
CHAPTER 12 ADVANCED INTELLIGENT SYSTEMS © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang.
1 Introduction to Artificial Neural Networks Andrew L. Nelson Visiting Research Faculty University of South Florida.
Machine Learning. Learning agent Any other agent.
MSE 2400 EaLiCaRA Spring 2015 Dr. Tom Way
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
Artificial Neural Networks
Artificial Neural Nets and AI Connectionism Sub symbolic reasoning.
Parallel Artificial Neural Networks Ian Wesley-Smith Frameworks Division Center for Computation and Technology Louisiana State University
IE 585 Introduction to Neural Networks. 2 Modeling Continuum Unarticulated Wisdom Articulated Qualitative Models Theoretic (First Principles) Models Empirical.
ANNs (Artificial Neural Networks). THE PERCEPTRON.
© Copyright 2004 ECE, UM-Rolla. All rights reserved A Brief Overview of Neural Networks By Rohit Dua, Samuel A. Mulder, Steve E. Watkins, and Donald C.
ARTIFICIAL NEURAL NETWORKS. Introduction to Neural Networks.
Appendix B: An Example of Back-propagation algorithm
Machine Learning Dr. Shazzad Hosain Department of EECS North South Universtiy
1 Machine Learning The Perceptron. 2 Heuristic Search Knowledge Based Systems (KBS) Genetic Algorithms (GAs)
NEURAL NETWORKS FOR DATA MINING
LINEAR CLASSIFICATION. Biological inspirations  Some numbers…  The human brain contains about 10 billion nerve cells ( neurons )  Each neuron is connected.
Artificial Neural Networks. The Brain How do brains work? How do human brains differ from that of other animals? Can we base models of artificial intelligence.
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Introduction to Machine Learning Instructor Shie-Jue Lee ( 李錫智 )
Artificial Neural Networks An Introduction. What is a Neural Network? A human Brain A porpoise brain The brain in a living creature A computer program.
1 Introduction to Neural Networks And Their Applications.
Neural Networks II By Jinhwa Kim. 2 Neural Computing is a problem solving methodology that attempts to mimic how human brain function Artificial Neural.
Neural Networks Steven Le. Overview Introduction Architectures Learning Techniques Advantages Applications.
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang 12-1 Chapter 12 Advanced Intelligent Systems.
© SEMINAR ON ARTIFICIAL NEURAL NETWORK AND ITS APPLICATIONS By Mr. Susant Kumar Behera Mrs. I. Vijaya.
Neural Network Basics Anns are analytical systems that address problems whose solutions have not been explicitly formulated Structure in which multiple.
Introduction to Neural Networks Introduction to Neural Networks Applied to OCR and Speech Recognition An actual neuron A crude model of a neuron Computational.
Neural Networks Presented by M. Abbasi Course lecturer: Dr.Tohidkhah.
Dr.Abeer Mahmoud ARTIFICIAL INTELLIGENCE (CS 461D) Dr. Abeer Mahmoud Computer science Department Princess Nora University Faculty of Computer & Information.
IE 585 History of Neural Networks & Introduction to Simple Learning Rules.
Artificial Intelligence CIS 342 The College of Saint Rose David Goldschmidt, Ph.D.
Nicolas Galoppo von Borries COMP Motion Planning Introduction to Artificial Neural Networks.
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
Business Intelligence and Decision Support Systems (9 th Ed., Prentice Hall) Chapter 6: Artificial Neural Networks for Data Mining.
INTRODUCTION TO NEURAL NETWORKS 2 A new sort of computer What are (everyday) computer systems good at... and not so good at? Good at..Not so good at..
Business Intelligence and Decision Support Systems (9 th Ed., Prentice Hall) Chapter 6: Artificial Neural Networks for Data Mining.
Introduction.
Artificial Intelligence (CS 370D)
CSSE463: Image Recognition Day 17
Chapter 12 Advanced Intelligent Systems
Introduction.
XOR problem Input 2 Input 1
Introduction to Neural Networks And Their Applications - Basics
CSSE463: Image Recognition Day 17
Lecture Notes for Chapter 4 Artificial Neural Networks
CSSE463: Image Recognition Day 17
Artificial Neural Networks
CSSE463: Image Recognition Day 17
CSSE463: Image Recognition Day 17
Introduction.
David Kauchak CS51A Spring 2019
David Kauchak CS158 – Spring 2019
PYTHON Deep Learning Prof. Muhammad Saeed.
Presentation transcript:

Neural Networks and Their Applications John Paxton Montana State University August 14, 2003

Yellowstone National Park

Problem Domains Storing and recalling patterns Classifying patterns Mapping inputs onto outputs Grouping similar patterns Finding solutions to constrained optimization problems

Human Brain 10 billion neurons 60 trillion connections (synapses) soma axon dendrite

Human Brain Plastic Nonlinear Parallel Distributed Memory Distributed Processing

Artificial Neural Network input layer middle layer output layer

Comparison Biological Neural NetArtificial Neural Net SomaNeuron DendriteInput AxonOutput SynapseWeight

Neuron x1x2x3x1x2x3 y w1w2w3w1w2w3

Neuron Input -1 (absent) 0 (unknown) 1 (present)

Neuron Output X = ( ∑ x i w i ) y = fn ( X ) Common functions (fn) –sign function (-1 if X < 0, else 1) –sigmoid function (1 / (1 + e -x ) )

Perceptron OR concept sign function x 0 (1) x 1 x 2 2

Perceptron Can automatically learn the weights in a provable fashion! But can only learn linearly separable concepts. no yes no

Multilayer Neural Network Can include zero or more hidden layers Has a learning algorithm (backpropagation) that works in practice! XOR

Backpropagation Determine network topology Initialize weights Present a training example Apply inputs, calculate activations in middle layer, then calculate activations in output layer Calculate errors in output layer Calculate errors in hidden layer

Backpropagation Update weights Repeat process until some stopping condition is met Possible stopping conditions –largest error is below some threshold –total error is no longer decreasing –a time limit is exceeded

Clustering (Unsupervised) Traveling Salesperson Problem (6 cities) Kohonen Nets

Strengths Very versatile. They can predict, they can classify, they can cluster. They produce good results in complicated domains. Can handle categorical and continuous data. Available in many off-the-shelf products

Weaknesses All inputs must be massaged onto the range [ ]. Can not explain results. May converge on an inferior solution. Determining the topology is as much an art as it is a science. Might take a long time to converge.

Commercial Applications Neural networks were involved in more than 1 billion U.S. dollars in 1997!

Business Marketing –Microsoft. Direct mail marketing. –Albertsons. Determine the connection between buying diapers and buying beer. –BehavHeuristics Inc. Forecasts demand of airline flights. Real Estate –HNC. Automated Real Estate Appraisal.

Document and Form Processing Machine Printed Form Processing –Caere Corporation. Optical character recognition (FoxMaster). –Synaptics. Check reader. Hand Written Character Recognition. –Eastman Kodak. Forms processing for UK motor vehicle registration. –Fujitsu. Input to pen based computers.

Document and Form Processing Cursive Handwriting Character Recognition –Apple Newton 120. Input to PDA. Graphic Recognition –Fein-Marquet Associates, Inc. Converts a hand drawn chemistry picture into a table.

Food Industry Odor/Aroma Analysis –Sharp. Cooking control via an electronic nose in a microwave oven. Produce Development –M&M/Mars. Improved chemical formulations of products.

Food Industry Quality Assurance –Anheuser-Busch. Beer testing. –Florida Department of Citrus. Pulp wash detection. –Frito-Lay. Potato chip testing.

Financial Industry Market Trading –Gerber Baby Foods. Cattle futures trading. –John Deere. Pension management. –Walkrich Investment Advisors. Stock valuation. Credit Rating –Chase Financial. Forecast credit worthiness.

Financial Industry Fraud Detection –Dunn and Bradstreet. Check approval. –HNC. Credit card fraud detection (Falcon). –Mastercard. Deviations in spending habits.

Energy Electrical Load Forecasting –Bayernwerk AG. Hydroelectric Dam Operation –Tauernkraftwerke. Dam displacement prediction. Natural Gas –Northern Natural Gas. Predict gas index prices.

Manufacturing Process Controllers –Nippon Steel. Continuous casting. –Siemans. Rolling mill. Quality Control Systems –Dunlop. Tires. –Intel. Computer chips. –Volvo. Diesel knock testing. Paint inspection.

Medical and Health Care Image Analysis –NeuroMedical Systems, Inc. Pap smears. Drug Development –Vysis Inc. Protein analysis Resource Allocation –Anderson Memorial Hospital. Predict use of hospital resources.

Science and Engineering Chemical Engineering –StellarNet Inc. Spectroscopy. Electrical Engineering –NeuroCad Inc. Optimized circuit routing. Weather –National Weather Service.

Transportation and Communication Transportation –London Underground. Fault detection. –Rolls Royce. Fault detection. Communication –AT&T/Lucent. Echo cancellation systems (more than 20 years).

Questions?