Multilayer Neural Networks

Size: px
Start display at page:

Download "Multilayer Neural Networks"

Transcription

1 Pattern Recognition Multilaer Neural Networs Lecture 4 Prof. Daniel Yeung School of Computer Science and Engineering South China Universit of Technolog Outline Introduction (6.) Artificial Neural Networ (6.) Multiple Laer Perceptron NN (6.) Bac-Propagation Algorithm (6.3) Regularization (6.) Relating NN and Baes Theor (6.6) (6.8) Lec4: Multilaer Neural Networs Lec4: Multilaer Neural Networs Introduction Recall, Linear Discriminant Functions: Introduction Solution : Mapping Function φ( x w x φ w x x 3 x 4 w Σ Σ g g x x 3 x 4 φ φ φ w Σ Σ g g x 5 x 5 φ Input Laer Output Laer Limited generalization capabilit Cannot handle the non-linearl separable problem Input Laer Output Laer Pro: Simple structure (still using LDF) Cons: Selection of φ( and its parameters Discuss alread in Lecture 03 Lec4: Multilaer Neural Networs 3 Lec4: Multilaer Neural Networs 4

2 Introduction Solution : Multi-Laer Neural Networ x w w 3 w x x 3 x 4 x 5 Σ g Σ g Multi-LaerNeural Networ (multilaer Perceptrons) The number of hidden laer should be more than one The hidden laers serve as a mapping function Will be introduced in this lecture Input Laer Hidden Laers Output Laer No need to choose the nonlinear mapping φ(, and no need to have an prior nowledge relevant to the classification problem. Lec4: Multilaer Neural Networs 5 Lec4: Multilaer Neural Networs 6 Artificial Neural Networ (ANN) A ver simplified model of the brain Human Brain input output Artificial Neural Networ (ANN) Composed of neurons which cooperate together input output Artificial NN Basicall a function approximator Transforms inputs into outputs to the best of its abilit Lec4: Multilaer Neural Networs 7 I w I w I d f Ө neuron input Lec4: Multilaer Neural Networs 8 w d snapse output

3 Artificial Neural Networ (ANN) Artificial Neural Networ (ANN) How does a neuron wor? The output of a neuron is a functionof the weighted sumof the inputsplus a bias (optional) unit which alwas emits a value of or - as a threshold. bias I I w I d w w d f Ө f(w I + w I + + w d I d + bias) activation function Lec4: Multilaer Neural Networs 9 Lec4: Multilaer Neural Networs 0 Artificial Neural Networ (ANN) Activation Function The function ( f ) is the activation function Examples: Artificial Neural Networ (ANN) XOR Example x+ x+ bias 0.5 x x ( ) sgn Linear Function Output is the same as input Differentiable f ( x Sign Function Decision Maing Not differentiable f ( x > 0 - x < 0 Sigmoid Function Smooth, continuous, and monotonicall increasing (differentiable) f ( /( + e -x ) Lec4: Multilaer Neural Networs x x x+ x.5 x Lec4: Multilaer Neural Networs x

4 Artificial Neural Networ (ANN) XOR Example x+ x+ x+ x x x sgn(++0.5) sgn(.5) sgn(+-.5) sgn(0.5) sgn( ) sgn(-.3) - ( ) sgn x - x - sgn( ) sgn(-.5) - sgn(---.5 ) sgn(-3.5) - sgn( ) sgn(-.3) - Lec4: Multilaer Neural Networs 3 Artificial Neural Networ (ANN) XOR Example The first hidden unit implements an OR gate The second hidden unit an AND gate x+ x + The final output unit implements an AND NOT gate: AND NOT (x OR x ) AND NOT (x AND x ) x XOR x implements Lec4: Multilaer Neural Networs x+ x ( ) sgn.5 Artificial Neural Networ (ANN) Structure of ANN: Illustrative example: w w x w 3 Σ g x w w w 3 Σ g x Σ g x Σ g Input Laer Hidden Laers Output Laer Input Laer Hidden Laers Output Laer A simple three-laer neural networ Input Laer: input units Hidden Laer: 3 hidden units Output Laer: output units x length of salmon/seabass x lightness of salmon/seabass w i Weights for assigning importance of each input from neuron Top hidden neuron Length discriminant function Middle hidden neuron Combination of length and lightness discriminat function Bottom hidden neuron Lightness discriminant function g final output g final output Lec4: Multilaer Neural Networs 5 Lec4: Multilaer Neural Networs 6

5 Artificial Neural Networ (ANN) Artificial Neural Networ (ANN) x x w 3 w w net f w' net f f w f g f g A two-laer networ classifier can onl implement a linear decision boundar net d m w m x Input Laer Hidden Laers Output Laer m g ( ) f net f n net' Lec4: Multilaer Neural Networs 7 f w' i d i m w n i im x w' m i i ( ' ) g f net A three-, four-and higher-laer networs can implement arbitrardecision boundaries The decision regions need not be convex, nor simpl connected Lec4: Multilaer Neural Networs 8 Multiple Laer Perceptron NN (MLPNN) The most commonnn More thanone laer Sigmoid is used as activation function A general function approximator Not limited to linear problems Multilaers Multiple Laer Perceptron NN (MLPNN) Example Sigmoid function Input Laer Output Laer Lec4: Multilaer Neural Networs 9 Lec4: Multilaer Neural Networs 0

6 Training: Weight Determination Weights can be determined b training Reduce the errorbetween the desired outputs and the NN outputs of training samples Bac-propagation algorithmis the most widel used method for determining the weight Natural extension of LMS algorithm Pros: Simpleand generalmethod Cons: Slowand trapped at local minima Bac-Propagation (BP) Algorithm Calculation of the derivative flows bacwards through the networ Hence, it is called bacpropagation These derivatives point in the direction of themaximum increase of the error function (find out where max error being made and go bac to tr to decrease this error) A small step(learning rate) in the opposite directionwill result in the maximum decrease of the (local) error function: E w' w+ α where αis the learning rate & E the error function Lec4: Multilaer Neural Networs Lec4: Multilaer Neural Networs Bac-Propagation (BP) Algorithm Most common measure of error is the mean square error: J (target output) / Update ruleof weight is w( + ) w( ) η where ηis the learning rate which controls the size of each step Bac-Propagation (BP) Algorithm Next slides show BP for a 3-laer NN Two tpes of weights Hidden-to-Output w ho Input-to-Hidden w ih x x w ih w ho g g Lec4: Multilaer Neural Networs 3 Lec4: Multilaer Neural Networs 4

7 Bac-Propagation (BP) Algorithm 3-Laer NN The learning rule for the hidden-to-output units output output output f (net ) output net -(target -output ) n i w i Lec4: Multilaer Neural Networs 5 i output f' ( net ) output Bac-Propagation (BP) Algorithm 3-Laer NN The learning rule for the input-to-hidden units: i ( ) f net c c c net d m i w m c ( target? output ) ( target? output ) ( target? output ) x output output ( target? output) f' ( net ) w m ( net ) Lec4: Multilaer Neural Networs 6?? f output output output c d wmxm xi wi w i m Bac-Propagation (BP) Algorithm 3-Laer NN Summar Hidden-to-Output Weight Input-to-Hidden Weight i x f' i c ( net ) ( target? output ) f' ( net ) w f' ( net) ( target? ) output Bac-Propagation (BP) Algorithm Training Algorithm For the sample training set, the weights of NN can be updated differentl b presenting the training samples in different sequences There are two popular methods: Stochastic training Batch training Lec4: Multilaer Neural Networs 7 Lec4: Multilaer Neural Networs 8

8 Bac-Propagation (BP) Algorithm Training Algorithm Stochastic training Patterns are chosen randomlfrom the training set Networ weights are updated randoml Bac-Propagation (BP) Algorithm Training Algorithm Batch training All patterns are presentedto the networ before learning( weight update ) taes place Lec4: Multilaer Neural Networs 9 Lec4: Multilaer Neural Networs 30 Bac-Propagation (BP) Algorithm Training Algorithm A classifier with smaller training error is better? Most of the cases, NO! We have discussed this issue in Lecture 0 For example: Regularization In Lec03, we mentioned that in most cases, the solution (discriminant function) is not unique(ill-posed problem) Which one is the best? Enough to minimize training error? Too complex classifier? Good generalization abilit? (Stop training when testing error reaches a minimum) (Test unseen samples) Overfitting problem -- Minimize Remp Empirical Ris (Training Error) Lec4: Multilaer Neural Networs 3 Lec4: Multilaer Neural Networs 3

9 Regularization Regularizationis one of the methods to handle this problem ψ Add Regularization Term in obective function Measure the smoothness of the decision plane Tradeoff parameter (λ)to control the importanceof training accurac and regularization term See a smooth classifier with good performance on a training set Ma sacrifice Training Error for the Simplicit of a classifier if necessar Minimize: emp Tradeoff R +λψ( f) Regularization Minimize: emp R +λψ( f) λ: regularization parameter ; ψ regularization function λ 0 > λ > 0 λ Similar to traditional training obective faction No effect on the regularization term If we can find suitable λ, we ma find f with a good generalization abilit Dominated b the regularization term The most smooth classifier is found Training Error Regularization Term Lec4: Multilaer Neural Networs 33 Lec4: Multilaer Neural Networs 34 Regularization Weight Deca It is a well nown regularization example Regularization Term measures the value of weight f ψ ( ) Smaller smoother w The obective function becomes Minimize: Remp w +λ NN and Baes Theor Recall, Baes formula: ( x ω) p( ω) P( x, p( x ω ) p( ω ) p( p p( ω c i i i ω ) Suppose a networ is trained using the following target output setting: target( 0 if x ω otherwise Lec4: Multilaer Neural Networs 35 Lec4: Multilaer Neural Networs 36

10 NN and Baes Theor When the number of training samples tends to infinit (see p.304 in text): lim J( lim [ g( x; target] (Using mean square error for J) n n n n x 0 P( ω ) g ( x; p( x ω) dx+ P( ω ) g ( x; p( x ω dx [ ] i g ( x; p( dx g( x; p( x, ω) dx+ [ g ( x; P( ω ] p( dx+ P( ω P i ) p( x, ω dx ) dx ( ωi p( Dependent on w Independent of w We tr to minimize J( wrt w, the following term will be minimized [ ] g ( x; P( ω p( dx The trained networ will approximate the posteriori probabilit g ( x; P( ω Lec4: Multilaer Neural Networs 37 NN and Baes Theor Thus when MLPNNs are trained via bac propagation on a sum-squared errorcriterion, the provide a least squares fitto the Baes discriminant function, i.e. g ( x; P( ω Lec4: Multilaer Neural Networs 38 How to design a MLPNN to handle a given classification problem? x x... x n,,,... n Training Set??? MLP Must consider following issues: Scaling input Target values Number of Hidden Laers Number of Hidden Units Initializing Weights Learning Rates Momentum Weight Deca Stochastic and Batch Training Stopped Training Lec4: Multilaer Neural Networs 39 Lec4: Multilaer Neural Networs 40

11 Scaling input Featureswith different natures will have different properties(e.g. range, mean ) For example: Fish Mass (grams) and Length (meters) Normall the value of the mass will be orders of magnitude larger than that for length During the training, the networ will adust weights from the mass input unit far more than for the length input The error will hardl depend upon the tin length values The situation will be reversed when Mass (ilogram) and length (millimeter) Scaling input How to reduce this influence? Normalization(Standardization) Standardize the training samples have Same range (e.g. 0 to or - to ) Same variance (e.g. ) Same average (e.g. 0) Lec4: Multilaer Neural Networs 4 Lec4: Multilaer Neural Networs 4 Target Value Usuall a one-of-c representationfor the target vector is used For four-class problem: Four outputs will be used ω (, -, -, -) or (, 0, 0, 0) ω (-,, -, -) or (0,, 0, 0) ω 3 (-, -,, -) or (0, 0,, 0) ω 4 (-, -, -,-) or (0, 0, 0, ) Lec4: Multilaer Neural Networs 43 Number of Hidden Laers BP algorithm wors well for NN with man hidden laers, as long as the units are differentiable How man hidden laers are enough? NN with more hidden laers Easier to learn translations Some functions can be implemented more efficientl However, more undesirable local minima and more complex Since an arbitrar function can be approximated b a MLP with one hidden laer. Usuall a 3-laer NN is recommended. Special problem conditions or requirements ma ustif the use of more than 3- laers. Lec4: Multilaer Neural Networs 44

12 Number of Hidden Units Governs the expressive powerof the NN (for facial recognition, neuron for mouth, nose, ear, ee, face shape, etc.) Well separated or linearl separable samples, few hidden units Complicated problem, more hidden units One stud shows minimum Error occurs for NN in range Of 4-5 hidden units & range of weights 7-. Number of weight (n w ) Number of hidden units (n H ) Lec4: Multilaer Neural Networs 45 Number of Hidden Units How to determine the number of hidden units (n H )? n H determines the total number of weights in the net, thus we should not have more weights than the total number of training points (n) Without further information, n H cannot be determined before training Experimentall, Choose n H such that the total number of weights in the net is roughl n/0 Adust the complexitof the networ in response to the training data, for example, Start with a large value of n H Prune or eliminate weights Lec4: Multilaer Neural Networs 46 Initializing Weights In setting weights in a given laer, we choose weights randoml from a single distribution to help insure uniform learning If set w 0 initiall, learning can never start. Want standardize data so choose both positive & negative weights Initializing Weights If wis initiall too small the net activation of a hidden unit will be small and the linear modelwill be implemented net d m ( net ) w f mxm Sigmoid Function If wis initiall too large the hidden unit ma saturate (sigmoid function is alwas 0 or ) even before learning begins f ( /( + e -x ) Lec4: Multilaer Neural Networs 47 Saturate Linear Saturate Lec4: Multilaer Neural Networs 48

13 Initializing Weights We set wsuch that the net activation at a hidden unit is in the range < net < +, since net ±are the limits to its linear range Input-to-Hidden (d inputs ) < w i <+ d d Hidden-to-Output (the fan-in is n H ) < w <+ n n H Sigmoid Function f ( /( + e -x ) Lec4: Multilaer Neural Networs 49 H Learning Rates In principle, small learning rate ensures convergence Its value determines onl the learning speed but not the final weight values themselves However, in practice, because networs are rarel full trained to a training error minimum, the learning rate can affect the qualit of the final networ Lec4: Multilaer Neural Networs 50 Learning Rates Optimal learning rateis the one which leads to the local error minimum in one learning step J w Learning Rates The optimal rate: η opt J Slower convergence Optimal Converge b one step Oscillate but slowl converge Diverge Lec4: Multilaer Neural Networs 5 Lec4: Multilaer Neural Networs 5

14 Momentum What is Momentum? In phsics, it means the moving obects tend to eep moving unless acted upon b outside forces Example: Two balls carr the same momentum In BP algorithm, the approach is to alter the learning rule to include some fraction αof the previous weight update Different faction Momentum w( m+ ) w( m) + ( α) w( m) + α w( m ) Momentum without momentum with momentum Using momentum Reduces the variationin overall gradient directions Increase speed of learning Current delta w Previous delta w Lec4: Multilaer Neural Networs 53 Lec4: Multilaer Neural Networs 54 Stochastic and Batch Training Each training algorithm has strength and drawbac: Batch learningis tpicall slowerthan stochastic learning. Stochastic trainingis preferred for large redundant training sets Lec4: Multilaer Neural Networs 55 Stopped Training Stoppingthe training beforegradient descent is complete can help avoid overfitting A far more effective method is to stoptraining when the error on a separate validation set reaches a minimum Algorithm. Separate the original training set into two set New Training Set Validation Set. Use New Training Set to train the classifier 3. Evaluate the classifier using Validation Set at the end of each epoch Validation Error Training Error Generalization Error Lec4: Multilaer Neural Networs 56

Multilayer Neural Networks

Multilayer Neural Networks Pattern Recognition Lecture 4 Multilayer Neural Netors Prof. Daniel Yeung School of Computer Science and Engineering South China University of Technology Lec4: Multilayer Neural Netors Outline Introduction

More information

Pattern Classification

Pattern Classification Pattern Classification All materials in these slides were taen from Pattern Classification (2nd ed) by R. O. Duda,, P. E. Hart and D. G. Stor, John Wiley & Sons, 2000 with the permission of the authors

More information

Networks of McCulloch-Pitts Neurons

Networks of McCulloch-Pitts Neurons s Lecture 4 Netorks of McCulloch-Pitts Neurons The McCulloch and Pitts (M_P) Neuron x x sgn x n Netorks of M-P Neurons One neuron can t do much on its on, but a net of these neurons x i x i i sgn i ij

More information

Multilayer Perceptron

Multilayer 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 information

Multilayer Perceptron = FeedForward Neural Network

Multilayer Perceptron = FeedForward Neural Network Multilayer Perceptron = FeedForward Neural Networ History Definition Classification = feedforward operation Learning = bacpropagation = local optimization in the space of weights Pattern Classification

More information

Chapter 6: Backpropagation Nets

Chapter 6: Backpropagation Nets Chapter 6: Bacpropagation Nets Architecture: at least one laer of non-linear hidden units Learning: supervised, error driven, generalized delta rule Derivation of the weight update formula (with gradient

More information

Deep Neural Networks (1) Hidden layers; Back-propagation

Deep Neural Networks (1) Hidden layers; Back-propagation Deep Neural Networs (1) Hidden layers; Bac-propagation Steve Renals Machine Learning Practical MLP Lecture 3 4 October 2017 / 9 October 2017 MLP Lecture 3 Deep Neural Networs (1) 1 Recap: Softmax single

More information

Deep Neural Networks (1) Hidden layers; Back-propagation

Deep Neural Networks (1) Hidden layers; Back-propagation Deep Neural Networs (1) Hidden layers; Bac-propagation Steve Renals Machine Learning Practical MLP Lecture 3 2 October 2018 http://www.inf.ed.ac.u/teaching/courses/mlp/ MLP Lecture 3 / 2 October 2018 Deep

More information

Unit III. A Survey of Neural Network Model

Unit III. A Survey of Neural Network Model Unit III A Survey of Neural Network Model 1 Single Layer Perceptron Perceptron the first adaptive network architecture was invented by Frank Rosenblatt in 1957. It can be used for the classification of

More information

Machine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6

Machine 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 information

ECE 471/571 - Lecture 17. Types of NN. History. Back Propagation. Recurrent (feedback during operation) Feedforward

ECE 471/571 - Lecture 17. Types of NN. History. Back Propagation. Recurrent (feedback during operation) Feedforward ECE 47/57 - Lecture 7 Back Propagation Types of NN Recurrent (feedback during operation) n Hopfield n Kohonen n Associative memory Feedforward n No feedback during operation or testing (only during determination

More information

Introduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis

Introduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis Introduction to Natural Computation Lecture 9 Multilayer Perceptrons and Backpropagation Peter Lewis 1 / 25 Overview of the Lecture Why multilayer perceptrons? Some applications of multilayer perceptrons.

More information

Computational statistics

Computational 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

INF Introduction to classifiction Anne Solberg Based on Chapter 2 ( ) in Duda and Hart: Pattern Classification

INF Introduction to classifiction Anne Solberg Based on Chapter 2 ( ) in Duda and Hart: Pattern Classification INF 4300 151014 Introduction to classifiction Anne Solberg anne@ifiuiono Based on Chapter 1-6 in Duda and Hart: Pattern Classification 151014 INF 4300 1 Introduction to classification One of the most challenging

More information

Introduction to Neural Networks

Introduction to Neural Networks CUONG TUAN NGUYEN SEIJI HOTTA MASAKI NAKAGAWA Tokyo University of Agriculture and Technology Copyright by Nguyen, Hotta and Nakagawa 1 Pattern classification Which category of an input? Example: Character

More information

Lecture 16: Introduction to Neural Networks

Lecture 16: Introduction to Neural Networks Lecture 16: Introduction to Neural Networs Instructor: Aditya Bhasara Scribe: Philippe David CS 5966/6966: Theory of Machine Learning March 20 th, 2017 Abstract In this lecture, we consider Bacpropagation,

More information

ECE521 Lectures 9 Fully Connected Neural Networks

ECE521 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 information

Lecture 4: Perceptrons and Multilayer Perceptrons

Lecture 4: Perceptrons and Multilayer Perceptrons Lecture 4: Perceptrons and Multilayer Perceptrons Cognitive Systems II - Machine Learning SS 2005 Part I: Basic Approaches of Concept Learning Perceptrons, Artificial Neuronal Networks Lecture 4: Perceptrons

More information

Part 8: Neural Networks

Part 8: Neural Networks METU Informatics Institute Min720 Pattern Classification ith Bio-Medical Applications Part 8: Neural Netors - INTRODUCTION: BIOLOGICAL VS. ARTIFICIAL Biological Neural Netors A Neuron: - A nerve cell as

More information

Artifical Neural Networks

Artifical Neural Networks Neural Networks Artifical Neural Networks Neural Networks Biological Neural Networks.................................. Artificial Neural Networks................................... 3 ANN Structure...........................................

More information

Neural Networks. Chapter 18, Section 7. TB Artificial Intelligence. Slides from AIMA 1/ 21

Neural 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 information

Neural Networks. Nicholas Ruozzi University of Texas at Dallas

Neural Networks. Nicholas Ruozzi University of Texas at Dallas Neural Networks Nicholas Ruozzi University of Texas at Dallas Handwritten Digit Recognition Given a collection of handwritten digits and their corresponding labels, we d like to be able to correctly classify

More information

Multilayer Neural Networks

Multilayer Neural Networks Multilayer Neural Networks Multilayer Neural Networks Discriminant function flexibility NON-Linear But with sets of linear parameters at each layer Provably general function approximators for sufficient

More information

CS4442/9542b Artificial Intelligence II prof. Olga Veksler. Lecture 5 Machine Learning. Neural Networks. Many presentation Ideas are due to Andrew NG

CS4442/9542b Artificial Intelligence II prof. Olga Veksler. Lecture 5 Machine Learning. Neural Networks. Many presentation Ideas are due to Andrew NG CS4442/9542b Artificial Intelligence II prof. Olga Vesler Lecture 5 Machine Learning Neural Networs Many presentation Ideas are due to Andrew NG Outline Motivation Non linear discriminant functions Introduction

More information

Neural networks. Chapter 19, Sections 1 5 1

Neural 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 information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine 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 information

INF Anne Solberg One of the most challenging topics in image analysis is recognizing a specific object in an image.

INF Anne Solberg One of the most challenging topics in image analysis is recognizing a specific object in an image. INF 4300 700 Introduction to classifiction Anne Solberg anne@ifiuiono Based on Chapter -6 6inDuda and Hart: attern Classification 303 INF 4300 Introduction to classification One of the most challenging

More information

Lecture 5: Logistic Regression. Neural Networks

Lecture 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 information

Introduction to Machine Learning

Introduction to Machine Learning Introduction to Machine Learning Neural Networks Varun Chandola x x 5 Input Outline Contents February 2, 207 Extending Perceptrons 2 Multi Layered Perceptrons 2 2. Generalizing to Multiple Labels.................

More information

Multilayer Perceptron

Multilayer Perceptron Aprendizagem Automática Multilayer Perceptron Ludwig Krippahl Aprendizagem Automática Summary Perceptron and linear discrimination Multilayer Perceptron, nonlinear discrimination Backpropagation and training

More information

4. Multilayer Perceptrons

4. 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 information

AI Programming CS F-20 Neural Networks

AI Programming CS F-20 Neural Networks AI Programming CS662-2008F-20 Neural Networks David Galles Department of Computer Science University of San Francisco 20-0: Symbolic AI Most of this class has been focused on Symbolic AI Focus or symbols

More information

Serious limitations of (single-layer) perceptrons: Cannot learn non-linearly separable tasks. Cannot approximate (learn) non-linear functions

Serious limitations of (single-layer) perceptrons: Cannot learn non-linearly separable tasks. Cannot approximate (learn) non-linear functions BACK-PROPAGATION NETWORKS Serious limitations of (single-layer) perceptrons: Cannot learn non-linearly separable tasks Cannot approximate (learn) non-linear functions Difficult (if not impossible) to design

More information

Neural networks. Chapter 20. Chapter 20 1

Neural 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 information

INF Introduction to classifiction Anne Solberg

INF Introduction to classifiction Anne Solberg INF 4300 8.09.17 Introduction to classifiction Anne Solberg anne@ifi.uio.no Introduction to classification Based on handout from Pattern Recognition b Theodoridis, available after the lecture INF 4300

More information

ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD

ARTIFICIAL 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 information

Computational Intelligence Winter Term 2017/18

Computational Intelligence Winter Term 2017/18 Computational Intelligence Winter Term 207/8 Prof. Dr. Günter Rudolph Lehrstuhl für Algorithm Engineering (LS ) Fakultät für Informatik TU Dortmund Plan for Today Single-Layer Perceptron Accelerated Learning

More information

Neural Networks DWML, /25

Neural Networks DWML, /25 DWML, 2007 /25 Neural networks: Biological and artificial Consider humans: Neuron switching time 0.00 second Number of neurons 0 0 Connections per neuron 0 4-0 5 Scene recognition time 0. sec 00 inference

More information

Simple Neural Nets For Pattern Classification

Simple Neural Nets For Pattern Classification CHAPTER 2 Simple Neural Nets For Pattern Classification Neural Networks General Discussion One of the simplest tasks that neural nets can be trained to perform is pattern classification. In pattern classification

More information

LECTURE # - NEURAL COMPUTATION, Feb 04, Linear Regression. x 1 θ 1 output... θ M x M. Assumes a functional form

LECTURE # - NEURAL COMPUTATION, Feb 04, Linear Regression. x 1 θ 1 output... θ M x M. Assumes a functional form LECTURE # - EURAL COPUTATIO, Feb 4, 4 Linear Regression Assumes a functional form f (, θ) = θ θ θ K θ (Eq) where = (,, ) are the attributes and θ = (θ, θ, θ ) are the function parameters Eample: f (, θ)

More information

Neural networks and support vector machines

Neural networks and support vector machines Neural netorks and support vector machines Perceptron Input x 1 Weights 1 x 2 x 3... x D 2 3 D Output: sgn( x + b) Can incorporate bias as component of the eight vector by alays including a feature ith

More information

Neural networks. Chapter 20, Section 5 1

Neural 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 information

Computational Intelligence

Computational Intelligence Plan for Today Single-Layer Perceptron Computational Intelligence Winter Term 00/ Prof. Dr. Günter Rudolph Lehrstuhl für Algorithm Engineering (LS ) Fakultät für Informatik TU Dortmund Accelerated Learning

More information

Multilayer Perceptrons (MLPs)

Multilayer Perceptrons (MLPs) CSE 5526: Introduction to Neural Networks Multilayer Perceptrons (MLPs) 1 Motivation Multilayer networks are more powerful than singlelayer nets Example: XOR problem x 2 1 AND x o x 1 x 2 +1-1 o x x 1-1

More information

Neural Networks biological neuron artificial neuron 1

Neural Networks biological neuron artificial neuron 1 Neural Networks biological neuron artificial neuron 1 A two-layer neural network Output layer (activation represents classification) Weighted connections Hidden layer ( internal representation ) Input

More information

Multilayer Perceptrons and Backpropagation

Multilayer Perceptrons and Backpropagation Multilayer Perceptrons and Backpropagation Informatics 1 CG: Lecture 7 Chris Lucas School of Informatics University of Edinburgh January 31, 2017 (Slides adapted from Mirella Lapata s.) 1 / 33 Reading:

More information

Neural Networks (Part 1) Goals for the lecture

Neural Networks (Part 1) Goals for the lecture Neural Networks (Part ) Mark Craven and David Page Computer Sciences 760 Spring 208 www.biostat.wisc.edu/~craven/cs760/ Some of the slides in these lectures have been adapted/borrowed from materials developed

More information

Artificial Neural Network : Training

Artificial 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 information

NONLINEAR CLASSIFICATION AND REGRESSION. J. Elder CSE 4404/5327 Introduction to Machine Learning and Pattern Recognition

NONLINEAR 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 information

Last update: October 26, Neural networks. CMSC 421: Section Dana Nau

Last 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 information

ARTIFICIAL INTELLIGENCE. Artificial Neural Networks

ARTIFICIAL 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 information

Engineering Part IIB: Module 4F10 Statistical Pattern Processing Lecture 5: Single Layer Perceptrons & Estimating Linear Classifiers

Engineering Part IIB: Module 4F10 Statistical Pattern Processing Lecture 5: Single Layer Perceptrons & Estimating Linear Classifiers Engineering Part IIB: Module 4F0 Statistical Pattern Processing Lecture 5: Single Layer Perceptrons & Estimating Linear Classifiers Phil Woodland: pcw@eng.cam.ac.uk Michaelmas 202 Engineering Part IIB:

More information

epochs epochs

epochs epochs Neural Network Experiments To illustrate practical techniques, I chose to use the glass dataset. This dataset has 214 examples and 6 classes. Here are 4 examples from the original dataset. The last values

More information

Multilayer Neural Networks

Multilayer Neural Networks Multilayer Neural Networks Introduction Goal: Classify objects by learning nonlinearity There are many problems for which linear discriminants are insufficient for minimum error In previous methods, the

More information

Machine Learning. Neural Networks. Le Song. CSE6740/CS7641/ISYE6740, Fall Lecture 7, September 11, 2012 Based on slides from Eric Xing, CMU

Machine Learning. Neural Networks. Le Song. CSE6740/CS7641/ISYE6740, Fall Lecture 7, September 11, 2012 Based on slides from Eric Xing, CMU Machine Learning CSE6740/CS7641/ISYE6740, Fall 2012 Neural Networks Le Song Lecture 7, September 11, 2012 Based on slides from Eric Xing, CMU Reading: Chap. 5 CB Learning highly non-linear functions f:

More information

y(x n, w) t n 2. (1)

y(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 information

Feedforward Neural Networks

Feedforward Neural Networks Chapter 4 Feedforward Neural Networks 4. Motivation Let s start with our logistic regression model from before: P(k d) = softma k =k ( λ(k ) + w d λ(k, w) ). (4.) Recall that this model gives us a lot

More information

Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box

Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton Motivation Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses

More information

Neural Networks Lecture 3:Multi-Layer Perceptron

Neural Networks Lecture 3:Multi-Layer Perceptron Neural Networks Lecture 3:Multi-Layer Perceptron H.A Talebi Farzaneh Abdollahi Department of Electrical Engineering Amirkabir University of Technology Winter 2011 H. A. Talebi, Farzaneh Abdollahi Neural

More information

(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann

(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 information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine 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 information

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)

More information

Introduction to Artificial Neural Networks

Introduction 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 information

What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1

What 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 information

Lecture 13 Back-propagation

Lecture 13 Back-propagation Lecture 13 Bac-propagation 02 March 2016 Taylor B. Arnold Yale Statistics STAT 365/665 1/21 Notes: Problem set 4 is due this Friday Problem set 5 is due a wee from Monday (for those of you with a midterm

More information

Neural Networks Learning the network: Backprop , Fall 2018 Lecture 4

Neural 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 information

Machine Learning

Machine Learning Machine Learning 10-601 Maria Florina Balcan Machine Learning Department Carnegie Mellon University 02/10/2016 Today: Artificial neural networks Backpropagation Reading: Mitchell: Chapter 4 Bishop: Chapter

More information

Machine Learning

Machine Learning Machine Learning 10-315 Maria Florina Balcan Machine Learning Department Carnegie Mellon University 03/29/2019 Today: Artificial neural networks Backpropagation Reading: Mitchell: Chapter 4 Bishop: Chapter

More information

COMP 551 Applied Machine Learning Lecture 14: Neural Networks

COMP 551 Applied Machine Learning Lecture 14: Neural Networks COMP 551 Applied Machine Learning Lecture 14: Neural Networks Instructor: Ryan Lowe (ryan.lowe@mail.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted,

More information

Slide04 Haykin Chapter 4: Multi-Layer Perceptrons

Slide04 Haykin Chapter 4: Multi-Layer Perceptrons Introduction Slide4 Hayin Chapter 4: Multi-Layer Perceptrons CPSC 636-6 Instructor: Yoonsuc Choe Spring 28 Networs typically consisting of input, hidden, and output layers. Commonly referred to as Multilayer

More information

Speaker Representation and Verification Part II. by Vasileios Vasilakakis

Speaker Representation and Verification Part II. by Vasileios Vasilakakis Speaker Representation and Verification Part II by Vasileios Vasilakakis Outline -Approaches of Neural Networks in Speaker/Speech Recognition -Feed-Forward Neural Networks -Training with Back-propagation

More information

Mark Gales October y (x) x 1. x 2 y (x) Inputs. Outputs. x d. y (x) Second Output layer layer. layer.

Mark 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 information

CS:4420 Artificial Intelligence

CS: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 information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine 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 information

Pattern 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 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 information

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)

More information

Sections 18.6 and 18.7 Analysis of Artificial Neural Networks

Sections 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 information

SPSS, University of Texas at Arlington. Topics in Machine Learning-EE 5359 Neural Networks

SPSS, University of Texas at Arlington. Topics in Machine Learning-EE 5359 Neural Networks Topics in Machine Learning-EE 5359 Neural Networks 1 The Perceptron Output: A perceptron is a function that maps D-dimensional vectors to real numbers. For notational convenience, we add a zero-th dimension

More information

Artificial Neural Networks

Artificial 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 information

18.6 Regression and Classification with Linear Models

18.6 Regression and Classification with Linear Models 18.6 Regression and Classification with Linear Models 352 The hypothesis space of linear functions of continuous-valued inputs has been used for hundreds of years A univariate linear function (a straight

More information

Neural Networks and the Back-propagation Algorithm

Neural 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 information

Neural Networks. Learning and Computer Vision Prof. Olga Veksler CS9840. Lecture 10

Neural Networks. Learning and Computer Vision Prof. Olga Veksler CS9840. Lecture 10 CS9840 Learning and Computer Vision Prof. Olga Veksler Lecture 0 Neural Networks Many slides are from Andrew NG, Yann LeCun, Geoffry Hinton, Abin - Roozgard Outline Short Intro Perceptron ( layer NN) Multilayer

More information

Sections 18.6 and 18.7 Artificial Neural Networks

Sections 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 information

Neural Networks: Basics. Darrell Whitley Colorado State University

Neural Networks: Basics. Darrell Whitley Colorado State University Neural Networks: Basics Darrell Whitley Colorado State University In the Beginning: The Perceptron X1 W W 1,1 1,2 X2 W W 2,1 2,2 W source, destination In the Beginning: The Perceptron The Perceptron Learning

More information

Lab 5: 16 th April Exercises on Neural Networks

Lab 5: 16 th April Exercises on Neural Networks Lab 5: 16 th April 01 Exercises on Neural Networks 1. What are the values of weights w 0, w 1, and w for the perceptron whose decision surface is illustrated in the figure? Assume the surface crosses the

More information

Introduction to Neural Networks

Introduction 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 information

1 History of statistical/machine learning. 2 Supervised learning. 3 Two approaches to supervised learning. 4 The general learning procedure

1 History of statistical/machine learning. 2 Supervised learning. 3 Two approaches to supervised learning. 4 The general learning procedure Overview Breiman L (2001). Statistical modeling: The two cultures Statistical learning reading group Aleander L 1 Histor of statistical/machine learning 2 Supervised learning 3 Two approaches to supervised

More information

Engineering 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 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 information

Artificial Neural Networks Examination, June 2005

Artificial Neural Networks Examination, June 2005 Artificial Neural Networks Examination, June 2005 Instructions There are SIXTY questions. (The pass mark is 30 out of 60). For each question, please select a maximum of ONE of the given answers (either

More information

ECE662: Pattern Recognition and Decision Making Processes: HW TWO

ECE662: Pattern Recognition and Decision Making Processes: HW TWO ECE662: Pattern Recognition and Decision Making Processes: HW TWO Purdue University Department of Electrical and Computer Engineering West Lafayette, INDIANA, USA Abstract. In this report experiments are

More information

Lecture 17: Neural Networks and Deep Learning

Lecture 17: Neural Networks and Deep Learning UVA CS 6316 / CS 4501-004 Machine Learning Fall 2016 Lecture 17: Neural Networks and Deep Learning Jack Lanchantin Dr. Yanjun Qi 1 Neurons 1-Layer Neural Network Multi-layer Neural Network Loss Functions

More information

The perceptron learning algorithm is one of the first procedures proposed for learning in neural network models and is mostly credited to Rosenblatt.

The perceptron learning algorithm is one of the first procedures proposed for learning in neural network models and is mostly credited to Rosenblatt. 1 The perceptron learning algorithm is one of the first procedures proposed for learning in neural network models and is mostly credited to Rosenblatt. The algorithm applies only to single layer models

More information

Artificial neural networks

Artificial 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 information

An artificial neural networks (ANNs) model is a functional abstraction of the

An artificial neural networks (ANNs) model is a functional abstraction of the CHAPER 3 3. Introduction An artificial neural networs (ANNs) model is a functional abstraction of the biological neural structures of the central nervous system. hey are composed of many simple and highly

More information

Intelligent Systems Discriminative Learning, Neural Networks

Intelligent Systems Discriminative Learning, Neural Networks Intelligent Systems Discriminative Learning, Neural Networks Carsten Rother, Dmitrij Schlesinger WS2014/2015, Outline 1. Discriminative learning 2. Neurons and linear classifiers: 1) Perceptron-Algorithm

More information

Multilayer Neural Networks. (sometimes called Multilayer Perceptrons or MLPs)

Multilayer Neural Networks. (sometimes called Multilayer Perceptrons or MLPs) Multilayer Neural Networks (sometimes called Multilayer Perceptrons or MLPs) Linear separability Hyperplane In 2D: w x + w 2 x 2 + w 0 = 0 Feature x 2 = w w 2 x w 0 w 2 Feature 2 A perceptron can separate

More information

EEE 241: Linear Systems

EEE 241: Linear Systems EEE 4: Linear Systems Summary # 3: Introduction to artificial neural networks DISTRIBUTED REPRESENTATION An ANN consists of simple processing units communicating with each other. The basic elements of

More information

Multilayer Neural Networks. (sometimes called Multilayer Perceptrons or MLPs)

Multilayer Neural Networks. (sometimes called Multilayer Perceptrons or MLPs) Multilayer Neural Networks (sometimes called Multilayer Perceptrons or MLPs) Linear separability Hyperplane In 2D: w 1 x 1 + w 2 x 2 + w 0 = 0 Feature 1 x 2 = w 1 w 2 x 1 w 0 w 2 Feature 2 A perceptron

More information

Lecture 6. Notes on Linear Algebra. Perceptron

Lecture 6. Notes on Linear Algebra. Perceptron Lecture 6. Notes on Linear Algebra. Perceptron COMP90051 Statistical Machine Learning Semester 2, 2017 Lecturer: Andrey Kan Copyright: University of Melbourne This lecture Notes on linear algebra Vectors

More information

Stochastic gradient descent; Classification

Stochastic gradient descent; Classification Stochastic gradient descent; Classification Steve Renals Machine Learning Practical MLP Lecture 2 28 September 2016 MLP Lecture 2 Stochastic gradient descent; Classification 1 Single Layer Networks MLP

More information