Artificial Neural Networks (ANN) Xiaogang Su, Ph.D. Department of Mathematical Science University of Texas at El Paso
|
|
- Molly Butler
- 5 years ago
- Views:
Transcription
1 Artificial Neural Networks (ANN) Xiaogang Su, Ph.D. Department of Mathematical Science University of Texas at El Paso Fall, 2018
2 Outline Introduction A Brief History ANN Architecture Terminology Multi-Layer Perceptrons (MLP) Features of MLP Universal Approximation Radial Basis Function (RBF) Network Optimization Back-Prop Discussion
3 Introduction Introduction Neural Networks (NNs) are networks of neurons, for example, as found in real (i.e. biological) brains. Artificial Neural Networks (ANNs) are networks of Artificial Neurons, and hence constitute crude approximations to parts of real brains. They may be physical devices, or simulated on conventional computers. From a practical point of view, an ANN is just a parallel computational system consisting of many simple processing elements connected together in a specific way in order to perform a particular task. One should never lose sight of how crude the approximations are, and how over-simplified our ANNs are compared to real brains.
4 Introduction Human Brain & Neuron Cells Neural Networks: The flow of information includes feed-forward, feedback, and activation. The directed connections in ANN resemble the synapses.
5 Introduction Some Numbers about Brain vs. Computer There are approximately 10 billion neurons in the human cortex, compared with 10 of thousands of processors in the most powerful parallel computers. Each biological neuron is connected to several thousands of other neurons, similar to the connectivity in powerful parallel computers. Lack of processing units can be compensated by speed. The typical operating speeds of biological neurons is measured in milliseconds (10 3 s), while a silicon chip can operate in nanoseconds (10 9 s). The human brain is extremely energy efficient, using approximately joules per operation per second, whereas the best computers today use around 10 6 joules per operation per second. Brains have been evolving for tens of millions of years; computers have been evolving for tens of decades.
6 Introduction A Brief History A Brief History 1943 McCulloch and Pitts proposed the McCulloch-Pitts neuron model Hebb published The Organization of Behavior, in which the Hebbian learning rule was proposed Rosenblatt introduced Perceptrons Minsky and Papert s book Perceptrons demonstrated the limitation of Perceptrons, and almost the entire field went into hibernation Hopfield published on Hopfield networks Kohonen developed the Self-Organising Maps (SOM) that now bear his name The back-propagation learning algorithm for Multi-Layer Perceptrons (MLP) was re-discovered and the field took off again. 1990s 2000s 2010s The sub-field of Radial Basis Function Networks (RBFN) was developed. The power of Ensembles of ANN and SVM becomes apparent. Deep Learning revives the field.
7 ANN Architecture ANN Architecture
8 ANN Architecture Terminology Terms in ANN Units or Neurons Input units can be connected to hidden units or to output units (e.g., skip network) Hidden units can be connected to other hidden units or to output units. Output units cannot be connected to other units. Connections (directional synapses) The number of connections may depend on computing capacity. For example, the total number of connections in a network cannot exceed roughly 32,000 in SAS Enterprise Miner.
9 ANN Architecture Terminology Layers and Weights Layers All the units in a given layer share certain characteristics. For example, all the input units in a given layer have the same measurement level and the same method of standardization. All the units in a given hidden layer have the same combination function and the same activation function. All the units in a given output layer have the same combination function, activation function, and error function. Weights (e.g., coefficients in linear combinations), Bias and altitude (e.g., the intercept)
10 ANN Architecture Terminology Several Functions in ANN Combination Functions MLP: Linear combination in MLP RBF: Squared Euclidean distance between the vector of weights and the vector of values feeding into the unit and then multiply by the squared bias value (scale factor or inverse width) Activation Function: The value produced by the combination function is transformed by an activation function, e.g., Sigmoid, exponential, or softmax. Error Functions: The loss function, e.g, SSE in least squares or log-likelihood function
11 Multi-Layer Perceptrons (MLP) Features of MLP MLP - the Graphical Representation MLP can be viewed as a Multi-stage regression/classification model, with each stage corresponding to a parametric PPR.
12 Multi-Layer Perceptrons (MLP) Features of MLP Multi-Layer Perceptrons (MLP) Most popular form of neural network architecture. MLP is the default architecture in many Neural Network software. Features has any number of inputs. has one or more hidden layers with any number of units. uses linear combination functions in the hidden and output layers. uses sigmoid activation functions in the hidden layers. has any number of outputs with any activation function. has connections between the input layer and the first hidden layer, between the hidden layers, and between the last hidden layer and the output layer.
13 Multi-Layer Perceptrons (MLP) Universal Approximation MLP as Universal Approximator Given enough data, enough hidden units, and enough training time, an MLP with just one hidden layer can learn to approximate virtually any function to any degree of accuracy. Known as Universal Approximators. (A statistical analogy is approximating a function with nth order polynomials.) There are situations where a network with two or more hidden layers may require fewer hidden units and weights than a network with one hidden layer, so using extra hidden layers sometimes can improve generalization.
14 Multi-Layer Perceptrons (MLP) Universal Approximation MLP Function Approximation Illustration Consider the simple regression scenario where we have only one predictor X. The General idea of function approximation in MLP can be understood as follows Approximate a given function by a step function. Replace step functions with smooth sigmoid functions. The entire process can be represented via a MLP structure.
15 Multi-Layer Perceptrons (MLP) Universal Approximation Step Function Approximation
16 Multi-Layer Perceptrons (MLP) Universal Approximation MLP Graphical Structure The approximating step function can be written as y 0 + y 1 I (x x 1 ) + + y 4 I (x x 4 ) = y 0 + y 1 I ( x 1 + x 0) + + y 4 I ( x 4 + x 0)
17 Multi-Layer Perceptrons (MLP) Universal Approximation Sigmoid Approximation to the Threshold Function The threshold function can be approximated with a smooth sigmoid function. Many smooth sigmoid functions s( ) are available. Among them, the logistic or expit function is one. Namely, I (x > c) = I (x c > 0) exp(x c) = s(x c). 1 + exp(x c) In the example, replacing all steps functions with expit functions yields ŷ(x) = y 0 + y 1 s( x 1 + x) + + y 4 s( x 4 + x), which is exactly a MLP model.
18 Multi-Layer Perceptrons (MLP) Universal Approximation Sigmoid Function Approximation
19 Radial Basis Function (RBF) Network Radial Basis Function (RBF) Network First proposed by Broomhead and Lowe (1988). Features has any number of inputs. typically has only one hidden layer with any number of units. uses radial combination functions in the hidden layer, based on the squared Euclidean distance between the input vector and the weight vector. typically uses exponential or softmax activation functions (inducing two types) in the hidden layer, in which case the network is a Gaussian RBF network. uses linear combination functions in the output layer. can have multiple outputs with activation (output) function selected depending on the response type.
20 Radial Basis Function (RBF) Network Two Types of Gaussian RBF Networks The first type, ordinary RBF (ORBF) network, uses the exponential activation function, so the activation of the unit is a Gaussian bump as a function of the inputs. The second type, normalized RBF (NRBF) network, uses the softmax activation function, so the activations of all the hidden units are normalized to sum to one. While the distinction between these two types of Gaussian RBF architectures is sometimes mentioned in the NN literature, its importance has rarely been appreciated except by Tao (1993) and Werntges (1993).
21 Radial Basis Function (RBF) Network Ordinary RBF Networks Starting with the input layer x to hidden layer, Let u k be a unit in only hidden layer of a RBF network. In an ordinary RBF network, ( u k = exp w0k 2 x w k 2), for k = 1,..., K, where w k = (w 1k,..., w pk ) T. RBF network resembles kernel regression, in particular, the local linear regression in some way. The weights w k plays the role of an anchor/center point (or a typical observation) in each of the K clusters.
22 Radial Basis Function (RBF) Network Normalized RBF Networks In a normalized RBF network, first define [ e k = exp f ln(a k ) w0k 2 x w 2], for k = 1,..., K. Altitude parameters ak represents the maximum height of the component Gaussian functions. The constant f, the fan-in, is the number of connections to the neuron. Additional normalization is applied to obtain the unit at the hidden layer: u k u k := K k=1 u k so that K k=1 u k = 1. This amounts to activate with the softmax function, which is also routinely used multinomial logistic regression.
23 Radial Basis Function (RBF) Network RBF Network - Output Layer In the output layer, linear combinations are used as the combination function, i.e., ŷ = w 0 + w 1 u w K u K. The output activation function in RBF networks is customarily the identity function. Using an identity output activation function is a computational convenience in training, but it is possible and often desirable to use other output activation functions as in MLP.
24 Radial Basis Function (RBF) Network RBF Networks vs. MLP MLPs are said to be distributed-processing networks because the effect of a hidden unit can be distributed over the entire input space. On the other hand, Gaussian RBF networks are said to be local processing networks because the effect of a hidden unit is usually concentrated in a local area centered at the weight vector.
25 Radial Basis Function (RBF) Network An Example: RBF & MLP MLP g 1 0 (E(y)) = w 0 + w 1 u 1 + w 2 u 2 u 1 = tanh(w 01 + w 11 x 1 + w 21 x 2 + w 31 x 3 ) u 2 = tanh(w 02 + w 12 x 1 + w 22 x 2 + w 32 x 3 ) Ordinary RBF g 1 0 (E(y)) = w 0 + w 1 u 1 + w 2 u 2 [ u 1 = exp w 2 01 {(x 1 w 11 ) 2 + (x 2 w 21 ) 2 + (x 3 w 31 ) 2}] [ u 2 = exp w 2 02 {(x 1 w 12 ) 2 + (x 2 w 22 ) 2 + (x 3 w 32 ) 2}] Normalized RBF g 1 0 (E(y)) = w 1 u 1 + w 2 u 2 + w 3 u 3 e k u k := for k = 1, 2, 3 e 1 + e 2 + e + 3 [ e k = exp f ln(a i ) w 2 0k {(x 1 w 1k ) 2 + (x 2 w 2k ) 2 + (x 3 w 3k ) 2}]
26 Optimization Training Neural Networks Backprop (Back Propagation) provides an efficient way of computing derivatives (including gradient, Jacobian, and Hessian). Use the derivatives in optimization algorithms. Steepest descent: Batch Prop and Incremental Prop (stochastic gradient descent or online learning); Other optimization methods could be more reliable: Levenberg-Marquardt, Quasi-Newton, Conjugate Gradient, BFGS, and L-BFGS. Minimizing the empirical risk function for ANN is a nonconvex problem. Global optimization techniques may be helpful.
27 Discussion Other Issues ANN is not off-the-shelf and entails careful data preparation. Normalize input variables; Handle nominal/ordinal variables; Missing values need to be imputed. Training a good ANN model takes considerable experiences since there are so many parameters to be tuned, e.g., number of layers, number of hidden units, starting values for weights, tuning parameter for regularization, learning rate (step size in gradient descent). ANN lacks interpretability, although efforts have been made in terms of variable importance ranking, confidence intervals for weights, etc.
28 Discussion Discussion Thanks!
Artificial Neural Network and Fuzzy Logic
Artificial Neural Network and Fuzzy Logic 1 Syllabus 2 Syllabus 3 Books 1. Artificial Neural Networks by B. Yagnanarayan, PHI - (Cover Topologies part of unit 1 and All part of Unit 2) 2. Neural Networks
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) Human Brain Neurons Input-Output Transformation Input Spikes Output Spike Spike (= a brief pulse) (Excitatory Post-Synaptic Potential)
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward
More informationIntroduction to Neural Networks
Introduction to Neural Networks What are (Artificial) Neural Networks? Models of the brain and nervous system Highly parallel Process information much more like the brain than a serial computer Learning
More informationComputational statistics
Computational statistics Lecture 3: Neural networks Thierry Denœux 5 March, 2016 Neural networks A class of learning methods that was developed separately in different fields statistics and artificial
More information(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann
(Feed-Forward) Neural Networks 2016-12-06 Dr. Hajira Jabeen, Prof. Jens Lehmann Outline In the previous lectures we have learned about tensors and factorization methods. RESCAL is a bilinear model for
More informationNeural Networks. Chapter 18, Section 7. TB Artificial Intelligence. Slides from AIMA 1/ 21
Neural Networks Chapter 8, Section 7 TB Artificial Intelligence Slides from AIMA http://aima.cs.berkeley.edu / 2 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural
More informationIntroduction Biologically Motivated Crude Model Backpropagation
Introduction Biologically Motivated Crude Model Backpropagation 1 McCulloch-Pitts Neurons In 1943 Warren S. McCulloch, a neuroscientist, and Walter Pitts, a logician, published A logical calculus of the
More informationECE521 Lectures 9 Fully Connected Neural Networks
ECE521 Lectures 9 Fully Connected Neural Networks Outline Multi-class classification Learning multi-layer neural networks 2 Measuring distance in probability space We learnt that the squared L2 distance
More informationARTIFICIAL NEURAL NETWORKS گروه مطالعاتي 17 بهار 92
ARTIFICIAL NEURAL NETWORKS گروه مطالعاتي 17 بهار 92 BIOLOGICAL INSPIRATIONS Some numbers The human brain contains about 10 billion nerve cells (neurons) Each neuron is connected to the others through 10000
More informationLecture 4: Feed Forward Neural Networks
Lecture 4: Feed Forward Neural Networks Dr. Roman V Belavkin Middlesex University BIS4435 Biological neurons and the brain A Model of A Single Neuron Neurons as data-driven models Neural Networks Training
More informationNeural networks. Chapter 20, Section 5 1
Neural networks Chapter 20, Section 5 Chapter 20, Section 5 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 20, Section 5 2 Brains 0 neurons of
More informationArtificial Neural Networks. MGS Lecture 2
Artificial Neural Networks MGS 2018 - Lecture 2 OVERVIEW Biological Neural Networks Cell Topology: Input, Output, and Hidden Layers Functional description Cost functions Training ANNs Back-Propagation
More informationNONLINEAR CLASSIFICATION AND REGRESSION. J. Elder CSE 4404/5327 Introduction to Machine Learning and Pattern Recognition
NONLINEAR CLASSIFICATION AND REGRESSION Nonlinear Classification and Regression: Outline 2 Multi-Layer Perceptrons The Back-Propagation Learning Algorithm Generalized Linear Models Radial Basis Function
More informationFeedforward Neural Nets and Backpropagation
Feedforward Neural Nets and Backpropagation Julie Nutini University of British Columbia MLRG September 28 th, 2016 1 / 23 Supervised Learning Roadmap Supervised Learning: Assume that we are given the features
More informationSupervised (BPL) verses Hybrid (RBF) Learning. By: Shahed Shahir
Supervised (BPL) verses Hybrid (RBF) Learning By: Shahed Shahir 1 Outline I. Introduction II. Supervised Learning III. Hybrid Learning IV. BPL Verses RBF V. Supervised verses Hybrid learning VI. Conclusion
More informationArtificial Neural Networks
Artificial Neural Networks 鮑興國 Ph.D. National Taiwan University of Science and Technology Outline Perceptrons Gradient descent Multi-layer networks Backpropagation Hidden layer representations Examples
More informationNeural Networks and Deep Learning
Neural Networks and Deep Learning Professor Ameet Talwalkar November 12, 2015 Professor Ameet Talwalkar Neural Networks and Deep Learning November 12, 2015 1 / 16 Outline 1 Review of last lecture AdaBoost
More informationReading Group on Deep Learning Session 1
Reading Group on Deep Learning Session 1 Stephane Lathuiliere & Pablo Mesejo 2 June 2016 1/31 Contents Introduction to Artificial Neural Networks to understand, and to be able to efficiently use, the popular
More informationMachine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6
Machine Learning for Large-Scale Data Analysis and Decision Making 80-629-17A Neural Networks Week #6 Today Neural Networks A. Modeling B. Fitting C. Deep neural networks Today s material is (adapted)
More informationLast update: October 26, Neural networks. CMSC 421: Section Dana Nau
Last update: October 26, 207 Neural networks CMSC 42: Section 8.7 Dana Nau Outline Applications of neural networks Brains Neural network units Perceptrons Multilayer perceptrons 2 Example Applications
More informationNeural Networks and the Back-propagation Algorithm
Neural Networks and the Back-propagation Algorithm Francisco S. Melo In these notes, we provide a brief overview of the main concepts concerning neural networks and the back-propagation algorithm. We closely
More informationMultilayer Perceptron
Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Single Perceptron 3 Boolean Function Learning 4
More informationArtificial Neural Networks The Introduction
Artificial Neural Networks The Introduction 01001110 01100101 01110101 01110010 01101111 01101110 01101111 01110110 01100001 00100000 01110011 01101011 01110101 01110000 01101001 01101110 01100001 00100000
More informationNeural Networks. Nethra Sambamoorthi, Ph.D. Jan CRMportals Inc., Nethra Sambamoorthi, Ph.D. Phone:
Neural Networks Nethra Sambamoorthi, Ph.D Jan 2003 CRMportals Inc., Nethra Sambamoorthi, Ph.D Phone: 732-972-8969 Nethra@crmportals.com What? Saying it Again in Different ways Artificial neural network
More informationARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD
ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD WHAT IS A NEURAL NETWORK? The simplest definition of a neural network, more properly referred to as an 'artificial' neural network (ANN), is provided
More informationGrundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Neural networks Daniel Hennes 21.01.2018 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Logistic regression Neural networks Perceptron
More informationIntroduction to Artificial Neural Networks
Facultés Universitaires Notre-Dame de la Paix 27 March 2007 Outline 1 Introduction 2 Fundamentals Biological neuron Artificial neuron Artificial Neural Network Outline 3 Single-layer ANN Perceptron Adaline
More informationArtificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011!
Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011! 1 Todayʼs lecture" How the brain works (!)! Artificial neural networks! Perceptrons! Multilayer feed-forward networks! Error
More informationNeural networks. Chapter 20. Chapter 20 1
Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons Multilayer networks Applications of neural networks Chapter 20 2 Brains 10 11 neurons of > 20 types, 10 14 synapses, 1ms
More informationMachine Learning and Data Mining. Multi-layer Perceptrons & Neural Networks: Basics. Prof. Alexander Ihler
+ Machine Learning and Data Mining Multi-layer Perceptrons & Neural Networks: Basics Prof. Alexander Ihler Linear Classifiers (Perceptrons) Linear Classifiers a linear classifier is a mapping which partitions
More informationNeural networks. Chapter 19, Sections 1 5 1
Neural networks Chapter 19, Sections 1 5 Chapter 19, Sections 1 5 1 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 19, Sections 1 5 2 Brains 10
More informationData Mining Part 5. Prediction
Data Mining Part 5. Prediction 5.5. Spring 2010 Instructor: Dr. Masoud Yaghini Outline How the Brain Works Artificial Neural Networks Simple Computing Elements Feed-Forward Networks Perceptrons (Single-layer,
More informationCheng Soon Ong & Christian Walder. Canberra February June 2018
Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 2018 Outlines Overview Introduction Linear Algebra Probability Linear Regression
More informationNeural Networks: Introduction
Neural Networks: Introduction Machine Learning Fall 2017 Based on slides and material from Geoffrey Hinton, Richard Socher, Dan Roth, Yoav Goldberg, Shai Shalev-Shwartz and Shai Ben-David, and others 1
More informationNeural Networks Lecturer: J. Matas Authors: J. Matas, B. Flach, O. Drbohlav
Neural Networks 30.11.2015 Lecturer: J. Matas Authors: J. Matas, B. Flach, O. Drbohlav 1 Talk Outline Perceptron Combining neurons to a network Neural network, processing input to an output Learning Cost
More informationArtificial Neural Networks. Edward Gatt
Artificial Neural Networks Edward Gatt What are Neural Networks? Models of the brain and nervous system Highly parallel Process information much more like the brain than a serial computer Learning Very
More informationLecture 7 Artificial neural networks: Supervised learning
Lecture 7 Artificial neural networks: Supervised learning Introduction, or how the brain works The neuron as a simple computing element The perceptron Multilayer neural networks Accelerated learning in
More informationEE04 804(B) Soft Computing Ver. 1.2 Class 2. Neural Networks - I Feb 23, Sasidharan Sreedharan
EE04 804(B) Soft Computing Ver. 1.2 Class 2. Neural Networks - I Feb 23, 2012 Sasidharan Sreedharan www.sasidharan.webs.com 3/1/2012 1 Syllabus Artificial Intelligence Systems- Neural Networks, fuzzy logic,
More informationNeural Networks. Fundamentals of Neural Networks : Architectures, Algorithms and Applications. L, Fausett, 1994
Neural Networks Neural Networks Fundamentals of Neural Networks : Architectures, Algorithms and Applications. L, Fausett, 1994 An Introduction to Neural Networks (nd Ed). Morton, IM, 1995 Neural Networks
More informationAdvanced statistical methods for data analysis Lecture 2
Advanced statistical methods for data analysis Lecture 2 RHUL Physics www.pp.rhul.ac.uk/~cowan Universität Mainz Klausurtagung des GK Eichtheorien exp. Tests... Bullay/Mosel 15 17 September, 2008 1 Outline
More informationCOMP9444 Neural Networks and Deep Learning 2. Perceptrons. COMP9444 c Alan Blair, 2017
COMP9444 Neural Networks and Deep Learning 2. Perceptrons COMP9444 17s2 Perceptrons 1 Outline Neurons Biological and Artificial Perceptron Learning Linear Separability Multi-Layer Networks COMP9444 17s2
More informationLecture 10. Neural networks and optimization. Machine Learning and Data Mining November Nando de Freitas UBC. Nonlinear Supervised Learning
Lecture 0 Neural networks and optimization Machine Learning and Data Mining November 2009 UBC Gradient Searching for a good solution can be interpreted as looking for a minimum of some error (loss) function
More informationArtificial Neural Networks. Introduction to Computational Neuroscience Tambet Matiisen
Artificial Neural Networks Introduction to Computational Neuroscience Tambet Matiisen 2.04.2018 Artificial neural network NB! Inspired by biology, not based on biology! Applications Automatic speech recognition
More informationStatistical Machine Learning from Data
January 17, 2006 Samy Bengio Statistical Machine Learning from Data 1 Statistical Machine Learning from Data Multi-Layer Perceptrons Samy Bengio IDIAP Research Institute, Martigny, Switzerland, and Ecole
More informationArtificial neural networks
Artificial neural networks Chapter 8, Section 7 Artificial Intelligence, spring 203, Peter Ljunglöf; based on AIMA Slides c Stuart Russel and Peter Norvig, 2004 Chapter 8, Section 7 Outline Brains Neural
More informationy(x n, w) t n 2. (1)
Network training: Training a neural network involves determining the weight parameter vector w that minimizes a cost function. Given a training set comprising a set of input vector {x n }, n = 1,...N,
More informationMachine Learning. Neural Networks
Machine Learning Neural Networks Bryan Pardo, Northwestern University, Machine Learning EECS 349 Fall 2007 Biological Analogy Bryan Pardo, Northwestern University, Machine Learning EECS 349 Fall 2007 THE
More informationCourse 395: Machine Learning - Lectures
Course 395: Machine Learning - Lectures Lecture 1-2: Concept Learning (M. Pantic) Lecture 3-4: Decision Trees & CBC Intro (M. Pantic & S. Petridis) Lecture 5-6: Evaluating Hypotheses (S. Petridis) Lecture
More informationCSCI 252: Neural Networks and Graphical Models. Fall Term 2016 Prof. Levy. Architecture #7: The Simple Recurrent Network (Elman 1990)
CSCI 252: Neural Networks and Graphical Models Fall Term 2016 Prof. Levy Architecture #7: The Simple Recurrent Network (Elman 1990) Part I Multi-layer Neural Nets Taking Stock: What can we do with neural
More informationArtificial Intelligence
Artificial Intelligence Jeff Clune Assistant Professor Evolving Artificial Intelligence Laboratory Announcements Be making progress on your projects! Three Types of Learning Unsupervised Supervised Reinforcement
More informationCh.6 Deep Feedforward Networks (2/3)
Ch.6 Deep Feedforward Networks (2/3) 16. 10. 17. (Mon.) System Software Lab., Dept. of Mechanical & Information Eng. Woonggy Kim 1 Contents 6.3. Hidden Units 6.3.1. Rectified Linear Units and Their Generalizations
More informationSections 18.6 and 18.7 Artificial Neural Networks
Sections 18.6 and 18.7 Artificial Neural Networks CS4811 - Artificial Intelligence Nilufer Onder Department of Computer Science Michigan Technological University Outline The brain vs artifical neural networks
More informationECE521 Lecture 7/8. Logistic Regression
ECE521 Lecture 7/8 Logistic Regression Outline Logistic regression (Continue) A single neuron Learning neural networks Multi-class classification 2 Logistic regression The output of a logistic regression
More informationArtificial Neural Networks. Q550: Models in Cognitive Science Lecture 5
Artificial Neural Networks Q550: Models in Cognitive Science Lecture 5 "Intelligence is 10 million rules." --Doug Lenat The human brain has about 100 billion neurons. With an estimated average of one thousand
More informationMachine Learning Lecture 10
Machine Learning Lecture 10 Neural Networks 26.11.2018 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Today s Topic Deep Learning 2 Course Outline Fundamentals Bayes
More informationVasil Khalidov & Miles Hansard. C.M. Bishop s PRML: Chapter 5; Neural Networks
C.M. Bishop s PRML: Chapter 5; Neural Networks Introduction The aim is, as before, to find useful decompositions of the target variable; t(x) = y(x, w) + ɛ(x) (3.7) t(x n ) and x n are the observations,
More informationApprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning
Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Nicolas Thome Prenom.Nom@cnam.fr http://cedric.cnam.fr/vertigo/cours/ml2/ Département Informatique Conservatoire
More information2018 EE448, Big Data Mining, Lecture 5. (Part II) Weinan Zhang Shanghai Jiao Tong University
2018 EE448, Big Data Mining, Lecture 5 Supervised Learning (Part II) Weinan Zhang Shanghai Jiao Tong University http://wnzhang.net http://wnzhang.net/teaching/ee448/index.html Content of Supervised Learning
More informationSections 18.6 and 18.7 Artificial Neural Networks
Sections 18.6 and 18.7 Artificial Neural Networks CS4811 - Artificial Intelligence Nilufer Onder Department of Computer Science Michigan Technological University Outline The brain vs. artifical neural
More informationMachine Learning Lecture 12
Machine Learning Lecture 12 Neural Networks 30.11.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Course Outline Fundamentals Bayes Decision Theory Probability
More informationARTIFICIAL INTELLIGENCE. Artificial Neural Networks
INFOB2KI 2017-2018 Utrecht University The Netherlands ARTIFICIAL INTELLIGENCE Artificial Neural Networks Lecturer: Silja Renooij These slides are part of the INFOB2KI Course Notes available from www.cs.uu.nl/docs/vakken/b2ki/schema.html
More informationSTA 414/2104: Lecture 8
STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks Delivered by Mark Ebden With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable
More informationChapter ML:VI. VI. Neural Networks. Perceptron Learning Gradient Descent Multilayer Perceptron Radial Basis Functions
Chapter ML:VI VI. Neural Networks Perceptron Learning Gradient Descent Multilayer Perceptron Radial asis Functions ML:VI-1 Neural Networks STEIN 2005-2018 The iological Model Simplified model of a neuron:
More informationDEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY
DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY 1 On-line Resources http://neuralnetworksanddeeplearning.com/index.html Online book by Michael Nielsen http://matlabtricks.com/post-5/3x3-convolution-kernelswith-online-demo
More informationFeed-forward Network Functions
Feed-forward Network Functions Sargur Srihari Topics 1. Extension of linear models 2. Feed-forward Network Functions 3. Weight-space symmetries 2 Recap of Linear Models Linear Models for Regression, Classification
More informationSections 18.6 and 18.7 Analysis of Artificial Neural Networks
Sections 18.6 and 18.7 Analysis of Artificial Neural Networks CS4811 - Artificial Intelligence Nilufer Onder Department of Computer Science Michigan Technological University Outline Univariate regression
More informationArtifical Neural Networks
Neural Networks Artifical Neural Networks Neural Networks Biological Neural Networks.................................. Artificial Neural Networks................................... 3 ANN Structure...........................................
More informationInstituto Tecnológico y de Estudios Superiores de Occidente Departamento de Electrónica, Sistemas e Informática. Introductory Notes on Neural Networks
Introductory Notes on Neural Networs Dr. José Ernesto Rayas Sánche April Introductory Notes on Neural Networs Dr. José Ernesto Rayas Sánche BIOLOGICAL NEURAL NETWORKS The brain can be seen as a highly
More informationEngineering Part IIB: Module 4F10 Statistical Pattern Processing Lecture 6: Multi-Layer Perceptrons I
Engineering Part IIB: Module 4F10 Statistical Pattern Processing Lecture 6: Multi-Layer Perceptrons I Phil Woodland: pcw@eng.cam.ac.uk Michaelmas 2012 Engineering Part IIB: Module 4F10 Introduction In
More informationPattern Recognition Prof. P. S. Sastry Department of Electronics and Communication Engineering Indian Institute of Science, Bangalore
Pattern Recognition Prof. P. S. Sastry Department of Electronics and Communication Engineering Indian Institute of Science, Bangalore Lecture - 27 Multilayer Feedforward Neural networks with Sigmoidal
More informationWhat Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1
What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1 Multi-layer networks Steve Renals Machine Learning Practical MLP Lecture 3 7 October 2015 MLP Lecture 3 Multi-layer networks 2 What Do Single
More informationDeep Feedforward Networks
Deep Feedforward Networks Liu Yang March 30, 2017 Liu Yang Short title March 30, 2017 1 / 24 Overview 1 Background A general introduction Example 2 Gradient based learning Cost functions Output Units 3
More informationStatistical Machine Learning (BE4M33SSU) Lecture 5: Artificial Neural Networks
Statistical Machine Learning (BE4M33SSU) Lecture 5: Artificial Neural Networks Jan Drchal Czech Technical University in Prague Faculty of Electrical Engineering Department of Computer Science Topics covered
More informationNeural Nets in PR. Pattern Recognition XII. Michal Haindl. Outline. Neural Nets in PR 2
Neural Nets in PR NM P F Outline Motivation: Pattern Recognition XII human brain study complex cognitive tasks Michal Haindl Faculty of Information Technology, KTI Czech Technical University in Prague
More informationCS:4420 Artificial Intelligence
CS:4420 Artificial Intelligence Spring 2018 Neural Networks Cesare Tinelli The University of Iowa Copyright 2004 18, Cesare Tinelli and Stuart Russell a a These notes were originally developed by Stuart
More informationNeural Networks. Bishop PRML Ch. 5. Alireza Ghane. Feed-forward Networks Network Training Error Backpropagation Applications
Neural Networks Bishop PRML Ch. 5 Alireza Ghane Neural Networks Alireza Ghane / Greg Mori 1 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of
More informationNEURAL NETWORKS
5 Neural Networks In Chapters 3 and 4 we considered models for regression and classification that comprised linear combinations of fixed basis functions. We saw that such models have useful analytical
More informationArtificial Neural Networks 2
CSC2515 Machine Learning Sam Roweis Artificial Neural s 2 We saw neural nets for classification. Same idea for regression. ANNs are just adaptive basis regression machines of the form: y k = j w kj σ(b
More informationFeed-forward Networks Network Training Error Backpropagation Applications. Neural Networks. Oliver Schulte - CMPT 726. Bishop PRML Ch.
Neural Networks Oliver Schulte - CMPT 726 Bishop PRML Ch. 5 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of biological plausibility We will
More informationVorlesung Neuronale Netze - Radiale-Basisfunktionen (RBF)-Netze -
Vorlesung Neuronale Netze - Radiale-Basisfunktionen (RBF)-Netze - SS 004 Holger Fröhlich (abg. Vorl. von S. Kaushik¹) Lehrstuhl Rechnerarchitektur, Prof. Dr. A. Zell ¹www.cse.iitd.ernet.in/~saroj Radial
More informationNeural Networks Learning the network: Backprop , Fall 2018 Lecture 4
Neural Networks Learning the network: Backprop 11-785, Fall 2018 Lecture 4 1 Recap: The MLP can represent any function The MLP can be constructed to represent anything But how do we construct it? 2 Recap:
More informationArtificial Neural Network : Training
Artificial Neural Networ : Training Debasis Samanta IIT Kharagpur debasis.samanta.iitgp@gmail.com 06.04.2018 Debasis Samanta (IIT Kharagpur) Soft Computing Applications 06.04.2018 1 / 49 Learning of neural
More information4. Multilayer Perceptrons
4. Multilayer Perceptrons This is a supervised error-correction learning algorithm. 1 4.1 Introduction A multilayer feedforward network consists of an input layer, one or more hidden layers, and an output
More informationMIDTERM: CS 6375 INSTRUCTOR: VIBHAV GOGATE October,
MIDTERM: CS 6375 INSTRUCTOR: VIBHAV GOGATE October, 23 2013 The exam is closed book. You are allowed a one-page cheat sheet. Answer the questions in the spaces provided on the question sheets. If you run
More informationFrom perceptrons to word embeddings. Simon Šuster University of Groningen
From perceptrons to word embeddings Simon Šuster University of Groningen Outline A basic computational unit Weighting some input to produce an output: classification Perceptron Classify tweets Written
More informationArticle from. Predictive Analytics and Futurism. July 2016 Issue 13
Article from Predictive Analytics and Futurism July 2016 Issue 13 Regression and Classification: A Deeper Look By Jeff Heaton Classification and regression are the two most common forms of models fitted
More informationArtificial Neural Networks. Historical description
Artificial Neural Networks Historical description Victor G. Lopez 1 / 23 Artificial Neural Networks (ANN) An artificial neural network is a computational model that attempts to emulate the functions of
More informationOther Topologies. Y. LeCun: Machine Learning and Pattern Recognition p. 5/3
Y. LeCun: Machine Learning and Pattern Recognition p. 5/3 Other Topologies The back-propagation procedure is not limited to feed-forward cascades. It can be applied to networks of module with any topology,
More informationNeural Network Training
Neural Network Training Sargur Srihari Topics in Network Training 0. Neural network parameters Probabilistic problem formulation Specifying the activation and error functions for Regression Binary classification
More informationMark Gales October y (x) x 1. x 2 y (x) Inputs. Outputs. x d. y (x) Second Output layer layer. layer.
University of Cambridge Engineering Part IIB & EIST Part II Paper I0: Advanced Pattern Processing Handouts 4 & 5: Multi-Layer Perceptron: Introduction and Training x y (x) Inputs x 2 y (x) 2 Outputs x
More informationNeural Networks Lecture 4: Radial Bases Function Networks
Neural Networks Lecture 4: Radial Bases Function Networks H.A Talebi Farzaneh Abdollahi Department of Electrical Engineering Amirkabir University of Technology Winter 2011. A. Talebi, Farzaneh Abdollahi
More informationLecture 5: Logistic Regression. Neural Networks
Lecture 5: Logistic Regression. Neural Networks Logistic regression Comparison with generative models Feed-forward neural networks Backpropagation Tricks for training neural networks COMP-652, Lecture
More informationC4 Phenomenological Modeling - Regression & Neural Networks : Computational Modeling and Simulation Instructor: Linwei Wang
C4 Phenomenological Modeling - Regression & Neural Networks 4040-849-03: Computational Modeling and Simulation Instructor: Linwei Wang Recall.. The simple, multiple linear regression function ŷ(x) = a
More informationDeep Feedforward Networks. Seung-Hoon Na Chonbuk National University
Deep Feedforward Networks Seung-Hoon Na Chonbuk National University Neural Network: Types Feedforward neural networks (FNN) = Deep feedforward networks = multilayer perceptrons (MLP) No feedback connections
More informationLearning from Data: Multi-layer Perceptrons
Learning from Data: Multi-layer Perceptrons Amos Storkey, School of Informatics University of Edinburgh Semester, 24 LfD 24 Layered Neural Networks Background Single Neurons Relationship to logistic regression.
More informationLecture 3 Feedforward Networks and Backpropagation
Lecture 3 Feedforward Networks and Backpropagation CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago April 3, 2017 Things we will look at today Recap of Logistic Regression
More informationCS 4700: Foundations of Artificial Intelligence
CS 4700: Foundations of Artificial Intelligence Prof. Bart Selman selman@cs.cornell.edu Machine Learning: Neural Networks R&N 18.7 Intro & perceptron learning 1 2 Neuron: How the brain works # neurons
More informationFundamentals of Neural Network
Chapter 3 Fundamentals of Neural Network One of the main challenge in actual times researching, is the construction of AI (Articial Intelligence) systems. These systems could be understood as any physical
More information