Introduction to Neural Networks John Paxton Montana State University Summer 2003.

Slides:



Advertisements
Similar presentations
Multi-Layer Perceptron (MLP)
Advertisements

Backpropagation Learning Algorithm
NEURAL NETWORKS Backpropagation Algorithm
1 Machine Learning: Lecture 4 Artificial Neural Networks (Based on Chapter 4 of Mitchell T.., Machine Learning, 1997)
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.
CSC321: 2011 Introduction to Neural Networks and Machine Learning Lecture 7: Learning in recurrent networks Geoffrey Hinton.
CS 678 –Boltzmann Machines1 Boltzmann Machine Relaxation net with visible and hidden units Learning algorithm Avoids local minima (and speeds up learning)
Machine Learning: Connectionist McCulloch-Pitts Neuron Perceptrons Multilayer Networks Support Vector Machines Feedback Networks Hopfield Networks.
Modular Neural Networks CPSC 533 Franco Lee Ian Ko.
Machine Learning Neural Networks
Decision Support Systems
The back-propagation training algorithm
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
Rutgers CS440, Fall 2003 Neural networks Reading: Ch. 20, Sec. 5, AIMA 2 nd Ed.
1 Pendahuluan Pertemuan 1 Matakuliah: T0293/Neuro Computing Tahun: 2005.
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
Before we start ADALINE
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
Neural networks.
Optimization of thermal processes2007/2008 Optimization of thermal processes Maciej Marek Czestochowa University of Technology Institute of Thermal Machinery.
MSE 2400 EaLiCaRA Spring 2015 Dr. Tom Way
Neural Networks. Plan Perceptron  Linear discriminant Associative memories  Hopfield networks  Chaotic networks Multilayer perceptron  Backpropagation.
Artificial Neural Networks
Classification Part 3: Artificial Neural Networks
Presentation on Neural Networks.. Basics Of Neural Networks Neural networks refers to a connectionist model that simulates the biophysical information.
Computer Science and Engineering
Cascade Correlation Architecture and Learning Algorithm for Neural Networks.
Slides are based on Negnevitsky, Pearson Education, Lecture 12 Hybrid intelligent systems: Evolutionary neural networks and fuzzy evolutionary systems.
Neural NetworksNN 11 Neural netwoks thanks to: Basics of neural network theory and practice for supervised and unsupervised.
Neural Networks Ellen Walker Hiram College. Connectionist Architectures Characterized by (Rich & Knight) –Large number of very simple neuron-like processing.
Chapter 11 – Neural Networks COMP 540 4/17/2007 Derek Singer.
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
NEURAL NETWORKS FOR DATA MINING
Artificial Intelligence Methods Neural Networks Lecture 4 Rakesh K. Bissoondeeal Rakesh K. Bissoondeeal.
CS 478 – Tools for Machine Learning and Data Mining Backpropagation.
IE 585 Associative Network. 2 Associative Memory NN Single-layer net in which the weights are determined in such a way that the net can store a set of.
Simultaneous Recurrent Neural Networks for Static Optimization Problems By: Amol Patwardhan Adviser: Dr. Gursel Serpen August, 1999 The University of.
Optimization with Neural Networks Presented by: Mahmood Khademi Babak Bashiri Instructor: Dr. Bagheri Sharif University of Technology April 2007.
METU Informatics Institute Min720 Pattern Classification with Bio-Medical Applications Part 8: Neural Networks.
Neural Network Basics Anns are analytical systems that address problems whose solutions have not been explicitly formulated Structure in which multiple.
1 Lecture 6 Neural Network Training. 2 Neural Network Training Network training is basic to establishing the functional relationship between the inputs.
Artificial Neural Networks (Cont.) Chapter 4 Perceptron Gradient Descent Multilayer Networks Backpropagation Algorithm 1.
Neural Networks Teacher: Elena Marchiori R4.47 Assistant: Kees Jong S2.22
Chapter 18 Connectionist Models
CHAPTER 6 SPECIAL NETWORKS “Principles of Soft Computing, 2nd Edition”
Previous Lecture Perceptron W  t+1  W  t  t  d(t) - sign (w(t)  x)] x Adaline W  t+1  W  t  t  d(t) - f(w(t)  x)] f’ x Gradient.
Chapter 6 Neural Network.
Artificial Intelligence Methods Neural Networks Lecture 3 Rakesh K. Bissoondeeal Rakesh K. Bissoondeeal.
ECE 471/571 - Lecture 16 Hopfield Network 11/03/15.
1 Neural networks 2. 2 Introduction: Neural networks The nervous system contains 10^12 interconnected neurons.
Neural Networks Lecture 11: Learning in recurrent networks Geoffrey Hinton.
Deep Learning Overview Sources: workshop-tutorial-final.pdf
Supervised Learning – Network is presented with the input and the desired output. – Uses a set of inputs for which the desired outputs results / classes.
 Negnevitsky, Pearson Education, Lecture 12 Hybrid intelligent systems: Evolutionary neural networks and fuzzy evolutionary systems n Introduction.
J. Kubalík, Gerstner Laboratory for Intelligent Decision Making and Control Artificial Neural Networks II - Outline Cascade Nets and Cascade-Correlation.
1 Neural Networks MUMT 611 Philippe Zaborowski April 2005.
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..
CSE343/543 Machine Learning Mayank Vatsa Lecture slides are prepared using several teaching resources and no authorship is claimed for any slides.
Machine Learning Supervised Learning Classification and Regression
Neural networks.
Fall 2004 Backpropagation CS478 - Machine Learning.
Restricted Boltzmann Machines for Classification
BACKPROPAGATION Multlayer Network.
network of simple neuron-like computing elements
Artificial Neural Networks
CSC321: Neural Networks Lecture 11: Learning in recurrent networks
Presentation transcript:

Introduction to Neural Networks John Paxton Montana State University Summer 2003

Chapter 7: A Sampler Of Other Neural Nets Optimization Problems Common Extensions Adaptive Architectures Neocognitron

I. Optimization Problems Travelling Salesperson Problem. Map coloring. Job shop scheduling. RNA secondary structure.

Advantages of Neural Nets Can find near optimal solutions. Can handle weak (desirable, but not required) constraints.

TSP Topology Each row has 1 unit that is on Each column has 1 unit that is on City A City B City C 1 st 2 nd 3rd

Boltzmann Machine Hinton, Sejnowski (1983) Can be modelled using Markov chains Uses simulated annealing Each row is fully interconnected Each column is fully interconnected

Architecture u i,j connected to u k,j+1 with –d i,k u i1 connected to u kn with -d ik U 11 U n1 U nn U 1n b -p

Algorithm 1.Initialize weights b, p p > b p > greatest distance between cities Initialize temperature T Initialize activations of units to random binary values

Algorithm 2.while stopping condition is false, do steps 3 – 8 3.do steps 4 – 7 n 2 times (1 epoch) 4.choose i and j randomly 1 <= i, j <= n u ij is candidate to change state

Algorithm 5.Compute c = [1 – 2u ij ]b +  u km (-p) where k <> i, m <> j 6.Compute probability to accept change a = 1 / (1 + e (-c/T) ) 7.Accept change if random number [0..1] < a. If change, u ij = 1 – u ij 8.Adjust temperature T =.95T

Stopping Condition No state change for a specified number of epochs. Temperature reaches a certain value.

Example T(0) = 20 ½ units are on initially b = 60 p = cities, all distances less than or fewer epochs to find stable configuration in 100 random trials

Other Optimization Architectures Continuous Hopfield Net Gaussian Machine Cauchy Machine –Adds noise to input in attempt to escape from local minima –Faster annealing schedule can be used as a consequence

II. Extensions Modified Hebbian Learning –Find parameters for optimal surface fit of training patterns

Boltzmann Machine With Learning Add hidden units net below could be used for simple encoding/decoding (data compression) x1x1 x2x2 z1z1 y2y2 y1y1

Simple Recurrent Net Learn sequential or time varying patterns Doesn’t necessarily have steady state output input units context units hidden units output units

Architecture x1x1 xnxn cpcp c1c1 zpzp z1z1 ymym y1y1

Simple Recurrent Net f(c i (t)) = f(z i (t-1)) f(c i (0)) = 0.5 Can use backpropagation Can learn string of characters

Example: Finite State Automaton 4 x i 4 y i 2 z i 2 c i BEGIN A B END

Backpropagation In Time Rumelhart, Williams, Hinton (1986) Application: Simple shift register x1 x2 z1 y2 y1 x2 x1 1 (fixed)

Backpropagation Training for Fully Recurrent Nets Adapts backpropagation to arbitrary connection patterns.

III. Adaptive Architectures Probabilistic Neural Net (Specht 1988) Cascade Correlation (Fahlman, Lebiere 1990)

Probabilistic Neural Net Builds its own architecture as training progresses Chooses class A over class B if h A c A f A (x) > h B c B f B (x) c A is the cost of classifying an example as belonging to A when it belongs to B h A is the a priori probability of an example belonging to class A

Probabilistic Neural Net f A (x) is the probability density function for class A, f A (x) is learned by the net z A1 : pattern unit, f A : summation unit x1x1 xnxn z Bk z B1 z Aj z A1 fBfB fAfA y

Cascade Correlation Builds own architecture while training progresses Tries to overcome slow rate of convergence by other neural nets Dynamically adds hidden units (as few as possible) Trains one layer at a time

Cascade Correlation Stage 1 x0x0 x1x1 x2x2 y2y2 y1y1

Cascade Correlation Stage 2 (fix weights into z 1 ) x0x0 x1x1 x2x2 y2y2 y1y1 z1z1

Cascade Correlation Stage 3 (fix weights into z2) x0x0 x1x1 x2x2 y2y2 y1y1 z1z1 z2z2

Algorithm 1.Train stage 1. If error is not acceptable, proceed. 2.Train stage 2. If error is not acceptable, proceed. 3.Etc.

IV. Neocognitron Fukushima, Miyako, Ito (1983) Many layers, hierarchical Very spare and localized connections Self organizing Supervised learning, layer by layer Recognizes handwritten 0, 1, 2, 3, … 9, regardless of position and style

Architecture Layer# of ArraysSize Input119 2 S1 / C112 / / 11 2 S2 / C238 / / 7 2 S3 / C332 / / 7 2 S4 / C416 / / 1 2

Architecture S layers respond to patterns C layers combine results, use larger field of view For example S 1 1 responds to

Training Progresses layer by layer S 1 connections to C 1 are fixed C 1 connections to S 2 are adaptable A V 2 layer is introduced between C 1 and S 2, V 2 is inhibatory C 1 to V 2 connections are fixed V 2 to S 2 connections are adaptable