Neural Networks. Neural Network. Neural Network. Neural Network 2/21/2008. Andrew Kusiak. Intelligent Systems Laboratory Seamans Center

Similar documents
A Dendrogram. Bioinformatics (Lec 17)

Introduction to Neural Networks

Neural Networks CMSC475/675

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

Data Mining. Neural Networks

11/14/2010 Intelligent Systems and Soft Computing 1

Artificial neural networks are the paradigm of connectionist systems (connectionism vs. symbolism)

11/14/2010 Intelligent Systems and Soft Computing 1

Optimization Methods for Machine Learning (OMML)

What is Data Mining? Data Mining. Data Mining Architecture. Illustrative Applications. Pharmaceutical Industry. Pharmaceutical Industry

What is Data Mining? Data Mining. Data Mining Architecture. Illustrative Applications. Pharmaceutical Industry. Pharmaceutical Industry

464 Index. Associative memory paradigms

Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network

Artificial Neural Networks MLP, RBF & GMDH

COMPUTATIONAL INTELLIGENCE

Data Set. What is Data Mining? Data Mining (Big Data Analytics) Illustrative Applications. What is Knowledge Discovery?

CP365 Artificial Intelligence

Learning. Learning agents Inductive learning. Neural Networks. Different Learning Scenarios Evaluation

Supervised Learning in Neural Networks (Part 2)

Machine Learning in Biology

CHAPTER 7 MASS LOSS PREDICTION USING ARTIFICIAL NEURAL NETWORK (ANN)

Function approximation using RBF network. 10 basis functions and 25 data points.

Neural Network Weight Selection Using Genetic Algorithms

Introduction to Machine Learning

LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS

Introduction to Multilayer Perceptrons

Chapter 5 Neural Network Concepts and Paradigms

Yuki Osada Andrew Cannon

Logical Rhythm - Class 3. August 27, 2018

Character Recognition Using Convolutional Neural Networks

Dr. Qadri Hamarsheh Supervised Learning in Neural Networks (Part 1) learning algorithm Δwkj wkj Theoretically practically

Neuro-Fuzzy Computing

Artificial Neural Networks for Detection of Malaria in RBCs. Purnima Pandit1, A. Anand2

Week 3: Perceptron and Multi-layer Perceptron

Neural Networks (Overview) Prof. Richard Zanibbi

MATLAB representation of neural network Outline Neural network with single-layer of neurons. Neural network with multiple-layer of neurons.

Classification Lecture Notes cse352. Neural Networks. Professor Anita Wasilewska

Artificial Neural Networks. Introduction to Computational Neuroscience Ardi Tampuu

CL7204-SOFT COMPUTING TECHNIQUES

Neural Networks. Robot Image Credit: Viktoriya Sukhanova 123RF.com

Data Mining and Evolutionary Computation Algorithms for Process Modeling and Optimization

CS 4510/9010 Applied Machine Learning. Neural Nets. Paula Matuszek Fall copyright Paula Matuszek 2016

^ Springer. Computational Intelligence. A Methodological Introduction. Rudolf Kruse Christian Borgelt. Matthias Steinbrecher Pascal Held

Review: Final Exam CPSC Artificial Intelligence Michael M. Richter

6. NEURAL NETWORK BASED PATH PLANNING ALGORITHM 6.1 INTRODUCTION

Climate Precipitation Prediction by Neural Network

Neural Networks in Statistica

Linear Models. Lecture Outline: Numeric Prediction: Linear Regression. Linear Classification. The Perceptron. Support Vector Machines

Optimizing Number of Hidden Nodes for Artificial Neural Network using Competitive Learning Approach

Multi-layer Perceptron Forward Pass Backpropagation. Lecture 11: Aykut Erdem November 2016 Hacettepe University

Artificial Neural Network Methodology for Modelling and Forecasting Maize Crop Yield

Machine Learning Classifiers and Boosting

Preprocessing DWML, /33

CSC 578 Neural Networks and Deep Learning

Slide07 Haykin Chapter 9: Self-Organizing Maps

CS 8520: Artificial Intelligence

An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting.

COMPUTATIONAL INTELLIGENCE

Artificial Neural Networks Unsupervised learning: SOM

Pattern Classification Algorithms for Face Recognition

Chapter 7: Competitive learning, clustering, and self-organizing maps

Assignment # 5. Farrukh Jabeen Due Date: November 2, Neural Networks: Backpropation

Neural Networks and Deep Learning

Computational Intelligence Meets the NetFlix Prize

Application of Support Vector Machine In Bioinformatics

4.12 Generalization. In back-propagation learning, as many training examples as possible are typically used.

Practical Tips for using Backpropagation

Use of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine

INTRODUCTION TO DEEP LEARNING

International Research Journal of Computer Science (IRJCS) ISSN: Issue 09, Volume 4 (September 2017)

Deep (1) Matthieu Cord LIP6 / UPMC Paris 6

Natural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu

Knowledge Discovery and Data Mining. Neural Nets. A simple NN as a Mathematical Formula. Notes. Lecture 13 - Neural Nets. Tom Kelsey.

Knowledge Discovery and Data Mining

Analytical model A structure and process for analyzing a dataset. For example, a decision tree is a model for the classification of a dataset.

of Artificial Neural Networks

Bioinformatics - Lecture 07

Evolutionary Computation: Solution Representation. Set Covering Problem. Set Covering Problem. Set Covering Problem 2/28/2008.

Autoorganised Structures for Extraction of Perceptual Primitives

Alex Waibel

Artificial Neural Networks (Feedforward Nets)

Data Warehousing and Machine Learning

Computer-Aided Diagnosis for Lung Diseases based on Artificial Intelligence: A Review to Comparison of Two- Ways: BP Training and PSO Optimization

Data Mining. Kohonen Networks. Data Mining Course: Sharif University of Technology 1

5 Learning hypothesis classes (16 points)

Dynamic Analysis of Structures Using Neural Networks

Introduction to Neural Networks: Structure and Training

Lecture #11: The Perceptron

Machine Learning in Telecommunications

FAST NEURAL NETWORK ALGORITHM FOR SOLVING CLASSIFICATION TASKS

RIMT IET, Mandi Gobindgarh Abstract - In this paper, analysis the speed of sending message in Healthcare standard 7 with the use of back

Balancing the flow. Part 3. Two-Machine Flowshop SCHEDULING SCHEDULING MODELS. Two-Machine Flowshop Two-Machine Job Shop Extensions

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

Machine Learning : Clustering, Self-Organizing Maps

Giri Narasimhan. CAP 5510: Introduction to Bioinformatics. ECS 254; Phone: x3748

CS6220: DATA MINING TECHNIQUES

Biologically inspired object categorization in cluttered scenes

Data Preprocessing. Supervised Learning

Lecture notes. Com Page 1

Perceptron as a graph

Transcription:

Neural Networks Neural Network Input Andrew Kusiak Intelligent t Systems Laboratory 2139 Seamans Center Iowa City, IA 52242-1527 andrew-kusiak@uiowa.edu http://www.icaen.uiowa.edu/~ankusiak Tel. 319-335 5934 Age = 51 Temperature = 40C Neuron 1 Neuron 2 Disease A = Yes Neuron 3 Neural Network Neural Network Age =.70 Temperature =.85 Neuron 1 Neuron 2 Weight 1 =.6 Neuron 3 Weight 2 =.2 Disease A =.59 (=.7.6 +.85.2) 1. Design a neural network structure. 2. Assign weights to the connectors. 3. Train the neural network. 4. Check for stopping criterion, e.g., training error or the network cross-validation. If the stopping criterion is not met, go to Step 3; otherwise go to Step 5. 5. Use the trained neural network for decision-making. 1

When NNs can be Used? Neural Networks are well understood s are well understood Historical data is available Applicable to a wide range of problems Good results even for complex domains Handling of categorical and continuous variables Off-the-shelf software is available Neural Networks in the range 0 to 1 s are produced in the range 0 to 1 Result are not explained May generate local optimum Solutions with errors Application Examples 1 Banking: Credit Application Evaluation Image Signal Processing: Data Compression Financial: Real Estate Appraisal Manufacturing: Manufacturing Process Control, Chemical Product Design Analysis Robotics: Vision Systems 2

Application Examples 2 Medicine: - Predict diagnosis - Determine diagnostic tests - Predict length of stay in a hospital - Predict treatment cost Biological Neuron vs Processing Element dendrites nucleus synapse axon cell body W 2 W 1 W n Σ y x θ Combination function Activation function Neural Networks Processing Elements Weighted Connections Activation Functions threshold function: sigmoid function: complex function: or linear function: W 2 W 1 Wn 1,x > 0 f ( x ) = 0, else 1 (1+ exp( x)) y x Σ θ (exp(x) exp( x)) (exp(x) + exp( x)) (2/(1+ exp( 2x))) 1 x Neural Network Types Architecture Feedforward Feedback (Loops) Learning Algorithm Supervised Unsupervised 3

Neural Network Types Supervised Feedforward Perceptron Multilayer Perceptron Cascade Correlation ART(Adaptive Resonance Theory) Map Unsupervised Feedforward ART 1&2 - Adaptive Resonance Theory 1&2 SOM (Self Organizing Map) Supervised & Unsupervised Feedforward RBF (Radial Basis Function) Counter Propagation Supervised Feedback Hopfield BAM (Bidirective Associate Memory) Boltzmann-Machine Feedforward NN i1 Example 1 i1 Example 2 i2 o i2 o i3 i3 Analogous to regression analysis Intermediate layer More powerful network 4

i1 i2 Example 3 o i1 i2 Example 4 o i3 i3 More neurons in the intermediate layer More powerful network with the increased risk of overfitting s Multiple output values Simple NN Application Illustrative Learning Rules $ spent/ month Age Gender Income Single intermediate layer NN Apparel Furniture Entertainment Hebbian (Hebb 1949) Winner-Takes-All (Competitive learning) (Kohonnen 1982) Simple error - correcting rule (Rosenblatt 1958) Backpropagation error - correcting rule (Werbos 1974) Propensity of making the next purchase Radial Basis Function (RBF) Network 5

Hebbian x1 x2 Learning wij yj y Winner-Takes-All x1 x2 Learning wi yj y x3 x3 t wij(t+1) = wij(t) + η yj(t)xi(t) 0 < η <1 learning rate The winning neuron s weight wi(t+1) = wi(t) + η(t) (X - wi(t)) X = input vector Learning Simple error - correcting rule x1 x2 x3 wi yj wij(t+1) = wij(t) + η (d - y) xi y d Desired output Learning Backpropagation error - correcting rule x1 x2 x3 wi yj y d Desired output w(t+1) = w(t) + η Δf(x(t+1), w(t)) (d(t +1)) - - f(x(t+1), w(t))) Δ = gradient 6

Learning Radial Basis Function (RBF) Network Features: Based on approximation and regularization theory Global optimum is more likely to be determined Short training time Simple topology Mathematical Model of a Neural Network Training Patterns x, f (x), for some unknown function f in a space of possible functions Φ and an error function E( f ˆ ), f ˆ Φ Function f ˆ that minimizes E( f ˆ ) Generalization NN is to generalize (examples) not to memorize Training Overfitting Prediction Problems: Overfitting Underfitting Network Size Good Generalization Overfitting 7

Number of Training Examples Given N nodes, W weights Steps for Building a Neural Network Model The number of training examples p Vapnik-Chervonenkis (VC) Dimension p O( W ε log N ε ) Widrow s rule of thumb p 10W Identify Problem Collect Data (Choose the training set) Preprocess Data Implement a Neural Network Choosing the Training Set NN Implementation The number of features - NN training time depends on the number of features - Number of example increases with the number of NN inputs Coverage of the range values of all features Number of outputs - Sufficient coverage in examples What kind of architecture is best for modeling the underlying problem? Which learning algorithm can achieve the best generalization? What size network gives the best generalization? How many training instances are required for good generalization? 8

Implementation Sequence 1. Normalize Data 2. Design a Network, e.g., #Layers, #Neurons and Transfer Function for Each Layer 3StT 3. Set Training ii Parameters 4. Provide Initial Weights and Save the Weights if Necessary 5. Training with a Learning Algorithm 6. Testing Matlab Implementation of NNs Getting Started and Quit % matlab >>...... >> quit Online Help >> help >> help which >> help lookfor >> help diary Variables >> a=1 >> a=1; >> A = 2 >> x = 4\1 % x = 1/4 >> C = astring % Don t forget >> b = [1 2 3] >> d = 1:3 >> e = 3:-1:1 % e = [3 2 1] >> g = [1 2 3... 4 5] % g = [ 1 2 3 4 5] Matrices >> B = [ 1 2 3; 4 5 6 7 8 9] >> P = [10 11 12], B=[B; P] >> zeros(3, 2) >> ones(2, 3) >> B(1, 2) >> B(:, 3) >> B(2, :) >> B(:, [1 3]) 9

Matrix Operations and Manipulation >> C = A*B >> B = B >> D = B + 2 >> E = B + B % E = 2 * B >> X = [1 2 3], Y=[4 5 6], Z = X.*Y >> X = A\B % A*X = B >> X = B/A % X*A = B >> Y = [] >> Y(:, [1 3])=[] NN and Genetic Algorithm Input 1 Input 2 Weight 1 Weight 2 11011000 11001111 Neuron 1 Neuron 2 Weight 1 Weight 2 Neuron 3 NN and Evolutionary Computation Input layer Intermediate layer layer Evolutionary computation algorithm 10