Supervised Learning Networks. Linear perceptron networks Multi-layer perceptrons Mixture of experts Decision-based neural networks Hierarchical neural.

Slides:



Advertisements
Similar presentations
Pattern Recognition and Machine Learning
Advertisements

Multi-Layer Perceptron (MLP)
ETHEM ALPAYDIN © The MIT Press, Lecture Slides for.
Support Vector Machines
Computer vision: models, learning and inference Chapter 8 Regression.
Supervised Learning Recap
Tuomas Sandholm Carnegie Mellon University Computer Science Department
Chapter 4: Linear Models for Classification
Supervised Learning: Linear Perceptron NN. Distinction Between Approximation- Based vs. Decision-Based NNs Teacher in Approximation-Based NN are quantitative.
Lecture 17: Supervised Learning Recap Machine Learning April 6, 2010.
Neural Networks II CMPUT 466/551 Nilanjan Ray. Outline Radial basis function network Bayesian neural network.
Radial-Basis Function Networks CS/CMPE 537 – Neural Networks.
ETHEM ALPAYDIN © The MIT Press, Lecture Slides for.
6/10/ Visual Recognition1 Radial Basis Function Networks Computer Science, KAIST.
RBF Neural Networks x x1 Examples inside circles 1 and 2 are of class +, examples outside both circles are of class – What NN does.
Slide 1 EE3J2 Data Mining EE3J2 Data Mining Lecture 15: Introduction to Artificial Neural Networks Martin Russell.
Radial Basis Function Networks 표현아 Computer Science, KAIST.
Supervised learning: Mixture Of Experts (MOE) Network.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
MACHINE LEARNING 12. Multilayer Perceptrons. Neural Networks Lecture Notes for E Alpaydın 2004 Introduction to Machine Learning © The MIT Press (V1.1)
CHAPTER 11 Back-Propagation Ming-Feng Yeh.
CS Instance Based Learning1 Instance Based Learning.
Aula 4 Radial Basis Function Networks
Review Rong Jin. Comparison of Different Classification Models  The goal of all classifiers Predicating class label y for an input x Estimate p(y|x)
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
Radial Basis Function G.Anuradha.
Radial-Basis Function Networks
Hazırlayan NEURAL NETWORKS Radial Basis Function Networks II PROF. DR. YUSUF OYSAL.
Radial Basis Function Networks
8/10/ RBF NetworksM.W. Mak Radial Basis Function Networks 1. Introduction 2. Finding RBF Parameters 3. Decision Surface of RBF Networks 4. Comparison.
Radial Basis Function Networks
Radial Basis Function Networks
This week: overview on pattern recognition (related to machine learning)
Machine Learning1 Machine Learning: Summary Greg Grudic CSCI-4830.
© N. Kasabov Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering, MIT Press, 1996 INFO331 Machine learning. Neural networks. Supervised.
Multi-Layer Perceptrons Michael J. Watts
Introduction to Neural Networks Debrup Chakraborty Pattern Recognition and Machine Learning 2006.
COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.
Machine Learning Lecture 11 Summary G53MLE | Machine Learning | Dr Guoping Qiu1.
RBF TWO-STAGE LEARNING NETWORKS: EXPLOITATION OF SUPERVISED DATA IN THE SELECTION OF HIDDEN UNIT PARAMETERS An application to SAR data classification.
Radial Basis Function Networks:
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 3: LINEAR MODELS FOR REGRESSION.
Ch 4. Linear Models for Classification (1/2) Pattern Recognition and Machine Learning, C. M. Bishop, Summarized and revised by Hee-Woong Lim.
Non-Bayes classifiers. Linear discriminants, neural networks.
1  The Problem: Consider a two class task with ω 1, ω 2   LINEAR CLASSIFIERS.
CS621 : Artificial Intelligence
Chapter 8: Adaptive Networks
Intro. ANN & Fuzzy Systems Lecture 13. MLP (V): Speed Up Learning.
METU Informatics Institute Min720 Pattern Classification with Bio-Medical Applications Part 9: Review.
Chapter 6 Neural Network.
Intro. ANN & Fuzzy Systems Lecture 38 Mixture of Experts Neural Network.
Artificial Intelligence Methods Neural Networks Lecture 3 Rakesh K. Bissoondeeal Rakesh K. Bissoondeeal.
Intro. ANN & Fuzzy Systems Lecture 16. Classification (II): Practical Considerations.
SUPERVISED AND UNSUPERVISED LEARNING Presentation by Ege Saygıner CENG 784.
Data Mining: Concepts and Techniques1 Prediction Prediction vs. classification Classification predicts categorical class label Prediction predicts continuous-valued.
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 1: INTRODUCTION.
CSE343/543 Machine Learning Mayank Vatsa Lecture slides are prepared using several teaching resources and no authorship is claimed for any slides.
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
Machine Learning Supervised Learning Classification and Regression
Adavanced Numerical Computation 2008, AM NDHU
LECTURE 11: Advanced Discriminant Analysis
Radial Basis Function G.Anuradha.
Overview of Supervised Learning
Dr. Unnikrishnan P.C. Professor, EEE
3. Applications to Speaker Verification
Neuro-Computing Lecture 4 Radial Basis Function Network
The Naïve Bayes (NB) Classifier
Introduction to Radial Basis Function Networks
Linear Discrimination
Lecture 16. Classification (II): Practical Considerations
Presentation transcript:

Supervised Learning Networks

Linear perceptron networks Multi-layer perceptrons Mixture of experts Decision-based neural networks Hierarchical neural networks

Two-Level: (b) Linear perceptron networks (c) decision-based neural network. (d) mixture of experts network. Hierarchical Neural Network Structures Three-Level: (e) experts-in-class network. (f) classes-in-expert network. One-Level: (a) multi-layer perceptrons.

Hierarchical Structure of NN 1-level hierarchy: BP 2-level hierarchy : MOE,DBNN 3-level hierarchy: PDBNN “Synergistic Modeling and Applications of Hierarchical Fuzzy Neural Networks”, by S.Y. Kung, et al., Proceedings of the IEEE, Special Issue on Computational Intelligence, Sept. 1999

All Classes in One Net multi-layer perceptron

Divide-and-conquer principle: divide the task into modules and then integrate the individual results into a collective decision. Modular Structures (two-level) Two typical modular networks: (1) mixture-of-experts (MOE) which utilizes the expert-level modules, (2) decision-based neural networks (DBNN) based on the class-level modules.

Each expert serves the function of (1) extracting local features and (2) making local recommendations. The rules in the gating network are used to decide how to combine recommendations from several local experts, with corresponding degree of confidences. Expert-level (Rule-level) Modules:

mixture of experts network

Class-level modules are natural basic partitioning units, where each module specializes in distinguishing its own class from the others. Class-level modules: In contrast to expert-level partitioning, this OCON structure facilitates a global (or mutual) supervised training scheme. In global inter-class supervised learning, any dispute over a pattern region by (two or more) competing classes may be effectively resolved by resorting to the teacher's guidance.

Decision Based Neural Network

Depending on the order used, two kinds of hierarchical networks: one has an experts-in-class construct and another a classes-in-expert Construct. Three-level hierarchical structures: Apply the divide-and-conquer principle twice: one time on the expert-level and another on the class-level.

Classes-in-Expert Network

Experts-in-Class Network

Multilayer Back-Propagation Networks

A BP Multi-Layer Perceptron(MLP) possesses adaptive learning abilities to estimate sampled functions, represent these samples, encode structural knowledge, and inference inputs to outputs via association. Its main strength lies in its (sufficiently large number of ) hidden units, thus a large number of interconnections. The MLP neural networks enhance the ability to learn and generalize from training data. Namely, MLP can approximate almost any function. BP Multi-Layer Perceptron(MLP)

A 3-Layer Network

Neuron Units: Activation Function

Linear Basis Function (LBF)

RBF NN is More Suitable for Probabilistic Pattern Classification MLP RBF HyperplaneKernel function The probability density function (also called conditional density function or likelihood) of the k-th class is defined as

The centers and widths of the RBF Gaussian kernels are deterministic functions of the training data; RBF BP Neural Network

According to Bays’ theorem, the posterior prob. is where P(C k ) is the prior prob. and RBF Output as Probability Function

MLPs are highly non-linear in the parameter space  gradient descent  local minima l RBF networks solve this problem by dividing the learning into two independent processes. 1. Use the K-mean algorithm to find c i and determine weights w using the least square method 2. RBF learning by gradient descent

Comparison of RBF and MLP

xpxp K-means K-Nearest Neighbor Basis Functions Linear Regression cici cici ii A w l RBF learning process

l RBF networks implement the function w i  i and c i can be determined separately  Fast learning algorithm l Basis function types

Finding the RBF Parameters (1 ) Use the K-mean algorithm to find c i

Centers and widths found by K-means and K-NN

Use K nearest neighbor rule to find the function width  k-th nearest neighbor of c i l The objective is to cover the training points so that a smooth fit of the training samples can be achieved

l For Gaussian basis functions Assume the variance  across each dimension are equal

l To write in matrix form, let

l Determining weights w using the least square method where d p is the desired output for pattern p

Let E be the total-squared error between the actual output and the target output

Note that Problems (1) Susceptible to round-off error. (2) No solution if is singular. (3) If is close to singular,we get very large component in w

Reasons (1) Inaccuracy in forming (2) If A is ill-conditioned, small change in A introduce large change in (3)If A T A is close to singular, dependent column in A T A exist e.g. two parallel straight lines. x y

singular matrix : If the lines are nearly parallel, they intersect each other at i.e. or So, the magnitude of the solution becomes very large; hence overflow will occur. The effect of the large components can be cancelled out if the machine precision is infinite.

If the machine precision is finite, we get large error. For example, Finite machine precision => Solution: Singular Value Decomposition

(2) RBF learning by gradient descent we have Apply

we have the following update equations

Elliptical Basis Function networks : function centers : covariance matrix

EBF Vs. RBF networks RBFN with 4 centersEBFN with 4 centers

MatLab Assignment #3: RBF BP Network to separate 2 classes RBF BP with 4 hidden unitsEBF BP with 4 hidden units ratio=2:1  