More on NNs This is lecture 17 of Biologically Inspired Computing; about NN applications, and overfitting.

Slides:



Advertisements
Similar presentations
Artificial Neural Networks
Advertisements

FUNCTION FITTING Student’s name: Ruba Eyal Salman Supervisor:
Artificial Intelligence 12. Two Layer ANNs
Multi-Layer Perceptron (MLP)
Beyond Linear Separability
Artificial Neural Networks (1)
Perceptron Learning Rule
NEURAL NETWORKS Perceptron
Data Mining (and machine learning) A few important things in brief top10dm, - neural networks – overfitting --- SVM.
CSCI 347 / CS 4206: Data Mining Module 07: Implementations Topic 03: Linear Models.
Machine Learning: Connectionist McCulloch-Pitts Neuron Perceptrons Multilayer Networks Support Vector Machines Feedback Networks Hopfield Networks.
Neural Network Oleh Danny Manongga
Brian Merrick CS498 Seminar.  Introduction to Neural Networks  Types of Neural Networks  Neural Networks with Pattern Recognition  Applications.
An introduction to: Deep Learning aka or related to Deep Neural Networks Deep Structural Learning Deep Belief Networks etc,
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Pattern Recognition using Hebbian Learning and Floating-Gates Certain pattern recognition problems have been shown to be easily solved by Artificial neural.
Introduction to Neural Networks Simon Durrant Quantitative Methods December 15th.
An Illustrative Example
Three kinds of learning
Lecture 4 Neural Networks ICS 273A UC Irvine Instructor: Max Welling Read chapter 4.
Hub Queue Size Analyzer Implementing Neural Networks in practice.
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
CIS 588 Neural Computing Course details. CIS 588 Neural Computing Course basics:  Instructor - Iren Valova  Tuesday, Thursday 5 - 6:15pm, T 101  1.
Radial Basis Function (RBF) Networks
Ranga Rodrigo April 5, 2014 Most of the sides are from the Matlab tutorial. 1.
Neural Networks Lecture 8: Two simple learning algorithms
November 25, 2014Computer Vision Lecture 20: Object Recognition IV 1 Creating Data Representations The problem with some data representations is that the.
Intro. ANN & Fuzzy Systems Lecture 2 Applications of ANN.
David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources:
Artificial Intelligence Lecture No. 28 Dr. Asad Ali Safi ​ Assistant Professor, Department of Computer Science, COMSATS Institute of Information Technology.
Artificial Neural Networks
Artificial Neural Nets and AI Connectionism Sub symbolic reasoning.
© Negnevitsky, Pearson Education, Will neural network work for my problem? Will neural network work for my problem? Character recognition neural.
1 Chapter 6: Artificial Neural Networks Part 2 of 3 (Sections 6.4 – 6.6) Asst. Prof. Dr. Sukanya Pongsuparb Dr. Srisupa Palakvangsa Na Ayudhya Dr. Benjarath.
Outline What Neural Networks are and why they are desirable Historical background Applications Strengths neural networks and advantages Status N.N and.
NEURAL NETWORKS FOR DATA MINING
Artificial Intelligence Lecture No. 29 Dr. Asad Ali Safi ​ Assistant Professor, Department of Computer Science, COMSATS Institute of Information Technology.
Artificial Intelligence Techniques Multilayer Perceptrons.
Neural Networks Automatic Model Building (Machine Learning) 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.
CSC321: Neural Networks Lecture 2: Learning with linear neurons Geoffrey Hinton.
1 Introduction to Neural Networks And Their Applications.
CS344: Introduction to Artificial Intelligence (associated lab: CS386) Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture 31: Feedforward N/W; sigmoid.
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.
Neural Networks II By Jinhwa Kim. 2 Neural Computing is a problem solving methodology that attempts to mimic how human brain function Artificial Neural.
Lesson Overview Lesson Overview What Is Science? Lesson Overview 1.1 What Is Science?
A.N.N.C.R.I.P.S The Artificial Neural Networks for Cancer Research in Prediction & Survival A CSI – VESIT PRESENTATION Presented By Karan Kamdar Amit.
CSC321 Introduction to Neural Networks and Machine Learning Lecture 3: Learning in multi-layer networks Geoffrey Hinton.
Neural Network Basics Anns are analytical systems that address problems whose solutions have not been explicitly formulated Structure in which multiple.
Back-Propagation Algorithm AN INTRODUCTION TO LEARNING INTERNAL REPRESENTATIONS BY ERROR PROPAGATION Presented by: Kunal Parmar UHID:
DLP Driven, Learning, Optical Neural Networks
CSC321: Lecture 7:Ways to prevent overfitting
Neural Networks Presented by M. Abbasi Course lecturer: Dr.Tohidkhah.
Neural Networks Teacher: Elena Marchiori R4.47 Assistant: Kees Jong S2.22
Dr.Abeer Mahmoud ARTIFICIAL INTELLIGENCE (CS 461D) Dr. Abeer Mahmoud Computer science Department Princess Nora University Faculty of Computer & Information.
Supervised Machine Learning: Classification Techniques Chaleece Sandberg Chris Bradley Kyle Walsh.
Each neuron has a threshold value Each neuron has weighted inputs from other neurons The input signals form a weighted sum If the activation level exceeds.
Web-Mining Agents Prof. Dr. Ralf Möller Universität zu Lübeck Institut für Informationssysteme Tanya Braun (Übungen)
Neural Networks Lecture 4 out of 4. Practical Considerations Input Architecture Output.
Neural networks (2) Reminder Avoiding overfitting Deep neural network Brief summary of supervised learning methods.
Deep Learning Overview Sources: workshop-tutorial-final.pdf
Artificial Neural Networks This is lecture 15 of the module `Biologically Inspired Computing’ An introduction to Artificial Neural Networks.
Neural Network Architecture Session 2
Perceptrons Lirong Xia.
Artificial Neural Networks
Introduction to Neural Networks And Their Applications - Basics
Artificial Intelligence 12. Two Layer ANNs
III. Introduction to Neural Networks And Their Applications - Basics
Artificial Neural Networks
Perceptrons Lirong Xia.
Presentation transcript:

More on NNs This is lecture 17 of Biologically Inspired Computing; about NN applications, and overfitting

NN Applications ANNs are a mature, tried and tested technology, used for all sorts of things. There are countless applications. Maybe ill-applied in many cases, maybe not trained ideally in many cases, and so on. However, the extent to which there are successful applications reveals: How useful it is to have some way of predicting/classifying without needing to know the “rules” underlying the task I.e. how much of an advance this BIC technology provides over “classical” methods. How basically flexible and reliable and scalable NNs are Next few slides contain application examples from just a single site about a single commercial NN package.

Stocks, Commodities and Futures Currency Price Predictions James O'Sullivan: Controls trading of more than 10 different financial markets with consistent profits. Corporate Bond Rating George Pugh: Predicts corporate bond ratings with 100% accuracy for consulting and trading. Standard and Poor's 500 Prediction LBS Capital Management, Inc: Predicts the S&P 500 one day ahead and one week ahead with better accuracy than traditional methods. Forecasting Stock Prices Walkrich Investments: Neural Networks rate underpriced stock; beating the S&P.

Business, Management, and Finance Direct Marketing Mail Prediction Microsoft: Improves response rates from 4.9% to 8.2%. Credit Scoring Herbert Jensen: Predicts loan application success with 75-80% accuracy. Identifing Policemen with Potential for Misconduct The Chicago Police Department predict misconduct potential based on employee records. Jury Summoning with Neural Networks The Montgomery Court House in Norristown, PA saves $70 million annually using The Intelligent Summoner from MEA. Forecasting Highway Maintenance with Neural Networks Professor Awad Hanna at the University of Wisconsin in Madison has trained a neural network to predict which type of concrete is better than another for a particular highway problem.

Medical Applications Breast Cancer Cell Analysis David Weinberg, MD: Image analysis ignores benign cells and classifies malignant cells. Hospital Expenses Reduced Anderson Memorial Hospital: Improves the quality of care, reduces death rate, and saved $500,000 in the first 15 months of use. Diagnosing Heart Attacks J. Furlong, MD: Recognizes Acute Myocardial Infarction from enzyme data Emergency Room Lab Test Ordering S. Berkov, MD: Saves time and money ordering tests using symptoms and demographics. Classifying Patients for Psychiatric Care G. Davis, MD: Predicts Length of Stay for Psychiatric Patients, saving money

Sports Applications Thoroughbred Horse Racing Don Emmons: 22 races, 17 winning horses. Thoroughbred Horse Racing Rich Janeva: 39% of winners picked at odds better than 4.5 to 1. Dog Racing Derek Anderson: 94% accuracy picking first place.

Science Solar Flare Prediction Dr. Henrik Lundstet: Predicts the next major solar flare; helps prevent problems for power plants. Mosquito Identification Aubrey Moore: 100% accuracy distinguishing between male and female, two species. Spectroscopy StellarNet Inc: Analyze spectral data to classify materials. Weather Forecasting Fort Worth National Weather Service: Predict rainfall to 85% accuracy. Air Quality Testing Researchers at the Defense Research Establishment Suffield, Chemical & Biological Defense Section, in Alberta, Canada have trained a neural network to recognize, classify and characterize aerosols of unknown origin with a high degree of accuracy.

Manufacturing Plastics Testing Monsanto: Predicts plastics quality, saving research time, processing time, and manufacturing expense. Computer Chip Manufacturing Quality Intel: Analyzes chip failures to help improve yields. Nondestructive Concrete Testing Donald G. Pratt: Detects the presence and position of flaws in reinforced concrete. Beer Testing Anheuser-Busch: Identifies the organic content of competitors' beer vapors with 96% accuracy. Steam Quality Testing AECL Research in Manitoba, Canada has developed the INSIGHT steam quality monitor, an instrument used to measure steam quality and mass flowrate.

Overfitting Suppose we train an NN to tell the difference between handwritten t and c, using only these examples: tsts cscs The ANN will learn easily. Either BP or some other method will quickly find weights for the NN which mean It gives 100% correct prediction on these cases.

Overfitting BUT; this NN will probably generalise very poorly. E.g. here is potential (very likely) performance on certain unseen cases Why? It will probably predict that this is a c It will probably predict that this is a t

Avoiding Overfitting It can be avoided by using as much training data as possible, ensuring as much diversity as possible in the data. This cuts down on the potential existence of features that might be discriminative in the training data, but are otherwise spurious. It can be avoided by jittering (adding noise). During training, every time an input pattern is presented, it is randomly perturbed. The idea of this is that spurious features will be `washed out’ by the noise, but valid discriminatory features will remain. The problem with this approach is how to correctly choose the level of noise.

Avoiding Overfitting II error Time (BP training, or EA/PSO generations) Training data Validation data Starting to overfit A typical curve showing performance during training. But here is performance on unseen data, not in the training set.

Avoiding Overfitting III 3. Another approach is early stopping. During training, keep track of the network’s performance on a separate validation set of data. At the point where error continues to improve on the training set, but starts to get worse on the validation set, that is when training should be stopped, since it is starting to overfit on the training data. The problem here is that this point is far from always clear cut.

Some other important NN points Input Layer Output layer Round nodes are `proper’ nodes, which work out a weighted sum of their inputs and send it on. Square `input nodes’ don’t really count – they just distribute the inputs. A NN like above, with just one layer of processing nodes, is called a perceptron. Perceptrons usually have many inputs and one output, but can have more than one output. They work out one (or more) weighted sums of their inputs.

Linear separability X=0 X=1 Y=0 Y= To the left, 1s and 0s are shown – these show the XOR of the x and y co- ordinates. Can you draw a straight line which has the 1s on one side of it and the 0s on the other side? It can’t be done; XOR is therefore not linearly separable It turns out that perceptrons cannot solve linearly inseparable classification problems. However, have just two layers of processing nodes, and all classification problems can be solved. Standard ANNs usually have 3 layers (input, hidden, output), and are sometimes called Multilayer Perceptrons

Perceptron can only draw one (hyper)line X=0 X=1 Y=0 Y=

Multilayer perceptron can only draw many (hyper)lines X=0 X=1 Y=0 Y= … but so can a perceptron. The difference is that the extra layer can make decisions based on what side of each line the data are on.

Talk to me …about how you would use an EA to evolve a neural network for a pattern recognition task. Encoding? Operators? Fitness ?

Next time Associative Networks (Hopfield) Self-Organising Maps