Institute of Computer Science, Prague 1 Neural Networks Marcel Jiřina.

Slides:



Advertisements
Similar presentations
Feed-forward Networks
Advertisements

Multi-Layer Perceptron (MLP)
Introduction to Support Vector Machines (SVM)
EE-M /7: IS L7&8 1/24, v3.0 Lectures 7&8: Non-linear Classification and Regression using Layered Perceptrons Dr Martin Brown Room: E1k
Slides from: Doug Gray, David Poole
EE 690 Design of Embodied Intelligence
1 Neural networks. Neural networks are made up of many artificial neurons. Each input into the neuron has its own weight associated with it illustrated.
An Introduction of Support Vector Machine
Support Vector Machines
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.
Decision Support Systems
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John Wiley.
Pseudoinverse Learning Algorithm for Feedforward Neural Networks Guo, Ping Department of Computer Science & Engineering, The Chinese University of Hong.
RBF Neural Networks x x1 Examples inside circles 1 and 2 are of class +, examples outside both circles are of class – What NN does.
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Neural Networks Part 4 Dan Simon Cleveland State University 1.
Carla P. Gomes CS4700 CS 4700: Foundations of Artificial Intelligence Prof. Carla P. Gomes Module: Neural Networks: Concepts (Reading:
An Illustrative Example
Prediction Networks Prediction –Predict f(t) based on values of f(t – 1), f(t – 2),… –Two NN models: feedforward and recurrent A simple example (section.
Chapter 6: Multilayer Neural Networks
CHAPTER 11 Back-Propagation Ming-Feng Yeh.
CS 4700: Foundations of Artificial Intelligence
CS Instance Based Learning1 Instance Based Learning.
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
8/10/ RBF NetworksM.W. Mak Radial Basis Function Networks 1. Introduction 2. Finding RBF Parameters 3. Decision Surface of RBF Networks 4. Comparison.
Neural networks.
Collaborative Filtering Matrix Factorization Approach
Dr. Hala Moushir Ebied Faculty of Computers & Information Sciences
Radial Basis Function Networks
Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks.
Multi Layer NN and Bit-True Modeling of These Networks SILab presentation Ali Ahmadi September 2007.
Neural NetworksNN 11 Neural netwoks thanks to: Basics of neural network theory and practice for supervised and unsupervised.
Artificial Neural Networks Shreekanth Mandayam Robi Polikar …… …... … net k   
Introduction to Neural Networks Debrup Chakraborty Pattern Recognition and Machine Learning 2006.
Chapter 3 Neural Network Xiu-jun GONG (Ph. D) School of Computer Science and Technology, Tianjin University
11 CSE 4705 Artificial Intelligence Jinbo Bi Department of Computer Science & Engineering
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John Wiley.
NEURAL NETWORKS FOR DATA MINING
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition LECTURE 16: NEURAL NETWORKS Objectives: Feedforward.
Classification / Regression Neural Networks 2
LINEAR CLASSIFICATION. Biological inspirations  Some numbers…  The human brain contains about 10 billion nerve cells ( neurons )  Each neuron is connected.
An Introduction to Support Vector Machine (SVM) Presenter : Ahey Date : 2007/07/20 The slides are based on lecture notes of Prof. 林智仁 and Daniel Yeung.
Chapter 6: Techniques for Predictive Modeling
A note about gradient descent: Consider the function f(x)=(x-x 0 ) 2 Its derivative is: By gradient descent. x0x0 + -
1 GMDH and Neural Network Application for Modeling Vital Functions of Green Algae under Toxic Impact Oleksandra Bulgakova, Volodymyr Stepashko, Tetayna.
METU Informatics Institute Min720 Pattern Classification with Bio-Medical Applications Part 8: Neural Networks.
Soft Computing Lecture 8 Using of perceptron for image recognition and forecasting.
Non-Bayes classifiers. Linear discriminants, neural networks.
CSSE463: Image Recognition Day 14 Lab due Weds, 3:25. Lab due Weds, 3:25. My solutions assume that you don't threshold the shapes.ppt image. My solutions.
1  The Problem: Consider a two class task with ω 1, ω 2   LINEAR CLASSIFIERS.
1 Lecture 6 Neural Network Training. 2 Neural Network Training Network training is basic to establishing the functional relationship between the inputs.
Neural Networks The Elements of Statistical Learning, Chapter 12 Presented by Nick Rizzolo.
Business Intelligence and Decision Support Systems (9 th Ed., Prentice Hall) Chapter 6: Artificial Neural Networks for Data Mining.
Business Intelligence and Decision Support Systems (9 th Ed., Prentice Hall) Chapter 6: Artificial Neural Networks for Data Mining.
Business Intelligence and Decision Support Systems (9 th Ed., Prentice Hall) Chapter 6: Artificial Neural Networks for Data Mining.
Machine Learning Supervised Learning Classification and Regression
Neural networks.
Deep Feedforward Networks
Neural Networks Winter-Spring 2014
One-layer neural networks Approximation problems
LECTURE 28: NEURAL NETWORKS
Collaborative Filtering Matrix Factorization Approach
Neuro-Computing Lecture 4 Radial Basis Function Network
CSE 573 Introduction to Artificial Intelligence Neural Networks
network of simple neuron-like computing elements
LECTURE 28: NEURAL NETWORKS
Introduction to Radial Basis Function Networks
Prediction Networks Prediction A simple example (section 3.7.3)
Presentation transcript:

Institute of Computer Science, Prague 1 Neural Networks Marcel Jiřina

Institute of Computer Science, Prague 2 Introduction Neural networks and their use to classification and other tasks ICS AS CR  Theoretical computer science  Neural networks, genetic alg. and nonlinear methods  Numeric algorithms..1 mil. eq.  Fuzzy sets, approximate reasoning, possibility th.  Applications: Nuclear science, Ecology, Meteorology, Reliability in machinery, Medical informatics …

Institute of Computer Science, Prague 3 Structure of talk NN classification Some theory Interesting paradigms NN and statistics NN and optimization and genetic algorithms About application of NN Conlusions

Institute of Computer Science, Prague 4 NN classification NE – not existing. Associated response can be arbitrary and then must be given - by teacher Feed-forward, recurrent Fixed structure - growing ApproximatorsAssociative memories GeneralPredictorsAuto- associative Hetero- associative Classifiers Teacher MLP-BP RBF GMDH NNSU Marks Klán Hopfield Perceptron(*)Hamming No teacher Kohonen Carpentier Grossberg (SOM) NEKohonen (NE) SignalsContinuous, real-valuedBinary, multi-valued (continuous)

Institute of Computer Science, Prague 5 Some theory Kolmogorov theorem Kůrková – Theorem Sigmoid transfer function 

Institute of Computer Science, Prague 6 MLP - BP Three layer - Single hidden layer MLP – 4 layer – 2 hidden Other paradigms have its own theory – another

Institute of Computer Science, Prague 7 Interesting paradigms Paradigm – general notion on structure, functions and algorithms of NN MLP - BP RBF GMDH NNSU All: approximators Approximator + thresholding = Classifier

Institute of Computer Science, Prague 8 MLP - BP MLP – error Back Propagation coefficients ,   (0,1) - Lavenberg-Marquart - Optimization tools MLP with jump transfer function - Optimization Feed – forward (in recall) Matlab, NeuralWorks, … Good when default is sufficient or when network is well tuned: Layers, neurons, , 

Institute of Computer Science, Prague 9 RBF Structure same as in MLP Bell-shaped transfer function (Gauss)  Number and positions of centers: random – cluster analysis  “broadness” of that bell  Size of individual bells  Learning methods Theory similar to MLP Matlab, NeuralWorks, … Good when default is sufficient or when network is well tuned : Layers mostly one hidden, # neurons, transfer function, proper cluster analysis (fixed No. of clusters, variable? Near – Far metric or criteria)

Institute of Computer Science, Prague 10 GMDH 1 (…5) Group Method Data Handling –Group – initially a pair of signals only “per partes” or successive polynomial approximator Growing network “parameterless” – parameter-barren –No. of new neurons in each layer only (processing time) –(output limits, stopping rule parameters) Overtraining – learning set is split to –Adjusting set –Evaluation set GMDH 2-5: neuron, growing network, learning strategy, variants

Institute of Computer Science, Prague 11 GMDH 2 – neuron Two inputs x 1, x 2 only –True inputs –Outputs from neurons of the preceding layer Full second order polynomial y = a x b x 1 x 2 + c x d x 1 + e x 2 + f y = neuron’s output n inputs => n(n-1)/2 neurons in the first layer Number of neurons grows exponentially Order of resulting polynomial grows exponentially: 2, 4, 8, 16, 32, … Ivakhnenko polynomials … some elements are missing

Institute of Computer Science, Prague 12 GMDH 3 – learning a neuron Matrix of data: inputs and desired value u 1, u 2, u 3, …, u n, y sample 1 …. sample m A pair of two u’s are neuron’s inputs x 1, x 2 m approximating equations, one for each sample a x b x 1 x 2 + c x d x 1 + e x 2 + f = y MatrixX  = Y  = (a, b, c, d, e, f) t  Each row of X is x 1 2 +x 1 x 2 +x 2 2 +x 1 +x 2 +1 LMS solution  = (X t X) -1 X t Y If X t X is singular, we omit this neuron

Institute of Computer Science, Prague 13 GMDH 4 - growing network x 1, x 2 y = desired output

Institute of Computer Science, Prague 14 GMDH 5 learn. strategy Problem: Number of neurons grows exponentially NN=n(n-1)2 Let the first layer of neurons grow unlimited In next rows:  [learning set split to adjusting set and evaluating set]  Compute parameters a,…f using adjusting set  Evaluate error using evaluating set and sort  Select some n best neurons and delete the others  Build the next layer OR  Stop learning if stopping condition is met.

Institute of Computer Science, Prague 15 GMDH 6 learn. Strategy 2 Select some n best neurons and delete the others Control parameter of GMDH network

Institute of Computer Science, Prague 16 GMDH 7 - variants Basic – full quadratic polynomial – Ivakh. poly Cubic, Fourth order simplified …  Reach higher order in less layers and less params Different stopping rules Different ratio of sizes of adjusting set and evaluating set

Institute of Computer Science, Prague 17 NNSU GA Neural Network with Switching Units learned by the use of Genetic Algorithm Approximator by lot of local hyper-planes; today also by local more general hyper-surfaces Feed-forward network Originally derived from MLP for optical implementation Structure looks like columns above individual inputs More … František

Institute of Computer Science, Prague 18 Learning and testing set Learning set  Adjusting (tuning) set  Evaluation set Testing set One data set – the splitting influences results Fair evaluation problem

Institute of Computer Science, Prague 19 NN and statistics MLP-BP mean squared error minimization  Sum of errors squared … MSE criterion  Hamming distance for (pure) classifiers No other statistical criteria or tests are in NN:  NN transforms data, generates mapping  statistical criteria or tests are outside NN (  2, K-S, C-vM,…) Is NN good for K-S test? … is y=sin(x) good for  2 test? Bayes classifiers, k-th nearest neighbor, kernel methods …

Institute of Computer Science, Prague 20 NN and optimization and genetic algorithms Learning is an optimization procedure Specific to given NN General optimization systems or methods Whole NN Parts – GMDH and NNSU - linear regression Genetic algorithm  Not only parameters, the structure, too  May be faster than iterations

Institute of Computer Science, Prague 21 About application of NN Soft problems  Nonlinear  Lot of noise  Problematic variables  Mutual dependence of variables Application areas  Economy  Pattern recognition  Robotics  Particle physics ……

Institute of Computer Science, Prague 22 Strategy when using NN For “soft problems” only NOT for  Exact function generation  periodic signals etc. First subtract all “systematics”  Nearly noise remains  Approximate this nearly noise  Add back all systematics Understand your paradigm  Tune it patiently or  Use “parameterless” paradigm

Institute of Computer Science, Prague 23 Conlusions Powerfull tool  Good when well used  Simple paradigm, complex behavior Special tool  Approximator  Classifier Universal tool  Very different problems  Soft problems