Machine Learning written examination

Size: px
Start display at page:

Download "Machine Learning written examination"

Transcription

1 Institutionen för informationstenologi Olle Gällmo Universitetsadjunt Adress: Lägerhyddsvägen 2 Box Uppsala Machine Learning written examination Friday, June 10, Allowed help material: Pen, paper and rubber, dictionary Telefon: Telefax: Hemsida: user.it.uu.se/~crwth Epost: olle.gallmo@it.uu.se Please, answer (in Swedish or English) the following questions to the best of your ability! Any assumptions made, which are not already part of the problem formulation, must be stated clearly in your answer! The maximum number of points is 40. To get the grade 3 (pass) a total of 20 points is required. The grade 4 requires 27 points and grade 5 requires 32 points. I will not be able to drop in to answer questions during this exam but Pontus will, sometime between 9.00 and Otherwise, as always, if something is unclear, just state your assumptions in your answer and you will probably be all right. Dept. of Information Technology Olle Gällmo Lecturer Address: Lägerhyddsvägen 2 Box 337 SE Uppsala SWEDEN Telephone: Telefax: In this exam, some concepts may be called by different names than the ones used in the boo. Here is a list of useful synonyms and acronyms: Perceptron = summation unit = SU = conventional neuron Binary perceptron = perceptron with binary activation function Multilayer perceptron = MLP = Feedforward networ of summation units Bac propagation = Generalized delta rule Standard Competitive Learning = LVQ-I without a neighbourhood function Good luc! 7 students wrote the exam. Two failed, four passed with grade 3 and one student passed with grade 4. Web site: user.it.uu.se/~crwth olle.gallmo@it.uu.se

2 1. Explain the two concepts pattern learning (= stochastic/online learning) and batch learning (= epoch/offline learning). From a theoretical (gradient descent) perspective, one is more correct than the other, which?... (3) Both learn from a finite training set by computing an error for each presented pattern and then the amount w ji by which the parameters in the learning system (e.g. the weights in a neural networ) should be changed to reduce that error. In pattern learning, the parameters are updated directly after each pattern presentation. This requires a random order of presentation, which is why this form of learning is sometimes called "stochastic". In batch learning the computed parameter changes are accumulated over time and the system is not updated until the whole training set has been presented once (one epoch). This is the more correct form of learning, from a gradient descent perspective (it is gradient descent). Points were deducted if the accumulation of changes were not mentioned in the description of batch learning. 2. Write down the equation and draw a graph of the logistic sigmoid function, often used as activation function in neural networs!... (2) f(x) = 1/(1+exp(-λx)). The steepness parameter λ was not required for full credit. Points deducted if the graph did not include ranges/axis. 3. Explain why a single binary perceptron can not solve the XOR problem!... (3) Binary perceptron classify by positioning a separating hyperplane between the classes. In the XOR-problem the classes are not separable by a hyperplane (a line, in this 2D-case). It requires at least two lines (see figure). Note that the word 'discriminant' does not imply anything about it's shape. A ellipse is also a disciminant, for example, and in that case it would suffice with one discriminant to solve the XOR-problem. So, the explanation here must state that the discriminant formed by binary perceptron is a hyperplane. 4. Write down a general recipe for how to derive a gradient descent learning rule (such as the delta rule or bac propagation), given a feedforward networ F(x) and an error function (objective function), E.... (4) Most students misunderstood the question. The general recipe ased for here was discussed and handed out on lecture 4. Deriving bacprop is an instantiation of that recipe (and gave partial credit, if done right). 5. Compare advantages and disadvantages of multilayer perceptrons (MLPs) and radial basis function networs (RBFs). The discussion must contain at least two examples where MLPs usually do better than RBFs and two examples where RBFs usually do better than MLPs.... (4) Se handout from lecture 10. Note that I ased for advantages/disadvantages, not for differences in how MLPs/RBFs are defined.

3 6. Let s assume that you are given a multilayer perceptron which is a blac box to you. You can see how many inputs and outputs there are, but you cannot pee inside to decide the number of hidden nodes, nor can you change any other internal properties of the networ. Let s also assume that you have a set of data (i.e. a set of input vectors with corresponding desired output vectors) representing some unnown target function. The inputs and output vectors in this set have the same dimensionality as the number of inputs and outputs of the networ, respectively. You are allowed to do what you wish with the given set of examples, but you will not be able to obtain more data. a) Suggest a method to find out if the networ is powerful enough (i.e. have enough hidden nodes) to find the target function!... (2) Train the networ on all the data you have, for a long time, i.e. try to overtrain the networ on purpose. If you can't get a low error even if allowed to do that, the networ is too small (or there are serious errors in the data). b) What bad effects can be expected if the networ is too large?... (2) You may overtrain the networ, i.e. lose the ability to generalize to unseen data. It also taes longer time, of course, but that is not the main problem. c) If the networ is too large, how can you avoid or minimize the bad effects when, as in this case, you are not allowed to change the size of the networ? (2) Split the data into at least three subsets a training set, a validation set and a test set so that you can decide when to stop training ('early stopping'). An alternative is to use K-fold cross validation, but you still need to mae sure that you don't train for too long. Noise injection also helps. 7. Unsupervised learning / Self organization a) How is standard competitive learning related to the classical method K-means?... (2) They are equivalent, if SCL is trained in batch learning mode. b) Explain the winner-taes-all problem which can occur in competitive learning!... (2) Competitive learning is to move the closest node (codeboo vector) towards the latest input vector, to mae it more liely to win also next time the same input vector is presented. The winner-taes-all problem occurs when a few nodes, in the extreme case only one node, wins all the time because they are closer to all the data than the other nodes (which never win and therefore never move). At best this leads to underutilization of the networ, at worst all the data is classified to the same class. c) When a new node is to be inserted in the Growing Neural Gas algorithm, it is inserted between two already existing nodes. Which two nodes?... (2) Inbetween the node x which has the greatest error and the node y among its current neighbours, with the greatest error. The error here is proporational to how much the node has moved lately (as a winner), so a great error indicates that the node is in an area with too few nodes to cover the data well.

4 8. Use the state transition graph below to explain temporal difference learning rewards: states: r r r s s s... values: a) Define values (V) recursively in terms of the following rewards and values!. (2) V(s) = r + γv(s') where γ is a discount factor. b) Show how values are updated, using the TD(0) learning rule!... (2) They are updated proportionally to the TD-error, which is the difference between the two sides of the equation from the previous question: V(s) := V(s) + η[r + γv(s') V(s)] c) TD(0) is a special case of a more general algorithm, called TD(λ) which includes eligibility traces. What is this?... (2) Instead of updating only the value from the previous state V(s), in TD(λ) we update all state values, but proportionally to how recently they were visited, which is measured by a slowly decaying variable, local for each state. The rate of this decay is controlled by the (global) λ parameter. TD(0), from the previous question, is an extreme case where the trace decays immediately and therefore only the latest state value is updated. 9. Population methods V(s) V(s ) V(s ) a) Explain the basic crossover mechanism used in Genetic Programming (GP). (2) Swap subtrees of the two parse trees, i.e. subexpressions of the two programs. Some students had confused Genetic Programming and Genetic Algorithms and described one-point crossover for GA (which gave no credit). b) Comparing the three Particle Swarm Optimization variants pbest, lbest and gbest, which one is most similar to random search? Which one is most liely to get stuc in local optima, due to premature convergence?... (2) In pbest, a particle only considers its personal best. It gets no information from the other particles, and pbest is therefore the most similar to random search (most chaotic). In gbest, particles strive for a weighted combination of their personal bests and the best position found by any particle in the swarm. This leads to a much more directed search with a tight swarm, where most particles strive in the same general direction. gbest is therefore the most liely to get stuc. lbest is a compromise between the two a generalization of the algorithm which contains pbest and gbest as two extremes. Here, a particle strives for a weighted combination of its personal best and the best of its neighbours (usually not the whole floc), defined by a neighbourhood graph.

5 c) When Ant Colony Optimization is used in the travelling salesman problem, the probability that ant moves from city i to city j at time t can be defined as follows: α β [ τ ij ( t) ] *[ η ] ij pij ( t) =, j C α β i [ τ ic( t) ] *[ ηic ] c C i Explain the right hand side of this equation!... (2) τ ij (t) is the amount of pheromones on the trail from city i to j (at time t it decays over time). η ij is the inverted distance from city i to j.the transition probability is a trade-off between these two, weighed by constants α and β.the sum over C is just for normaliation (to mae this a probability, i.e. so that it sums to 1). C is the set of feasible cities of ant (i.e. the remaining cities to visit).

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

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer

More information

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

4.12 Generalization. In back-propagation learning, as many training examples as possible are typically used. 1 4.12 Generalization In back-propagation learning, as many training examples as possible are typically used. It is hoped that the network so designed generalizes well. A network generalizes well when

More information

Artificial Neural Networks MLP, RBF & GMDH

Artificial Neural Networks MLP, RBF & GMDH Artificial Neural Networks MLP, RBF & GMDH Jan Drchal drchajan@fel.cvut.cz Computational Intelligence Group Department of Computer Science and Engineering Faculty of Electrical Engineering Czech Technical

More information

Review: Final Exam CPSC Artificial Intelligence Michael M. Richter

Review: Final Exam CPSC Artificial Intelligence Michael M. Richter Review: Final Exam Model for a Learning Step Learner initially Environm ent Teacher Compare s pe c ia l Information Control Correct Learning criteria Feedback changed Learner after Learning Learning by

More information

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

Learning. Learning agents Inductive learning. Neural Networks. Different Learning Scenarios Evaluation Learning Learning agents Inductive learning Different Learning Scenarios Evaluation Slides based on Slides by Russell/Norvig, Ronald Williams, and Torsten Reil Material from Russell & Norvig, chapters

More information

Learning and Generalization in Single Layer Perceptrons

Learning and Generalization in Single Layer Perceptrons Learning and Generalization in Single Layer Perceptrons Neural Computation : Lecture 4 John A. Bullinaria, 2015 1. What Can Perceptrons do? 2. Decision Boundaries The Two Dimensional Case 3. Decision Boundaries

More information

Neural Network Learning. Today s Lecture. Continuation of Neural Networks. Artificial Neural Networks. Lecture 24: Learning 3. Victor R.

Neural Network Learning. Today s Lecture. Continuation of Neural Networks. Artificial Neural Networks. Lecture 24: Learning 3. Victor R. Lecture 24: Learning 3 Victor R. Lesser CMPSCI 683 Fall 2010 Today s Lecture Continuation of Neural Networks Artificial Neural Networks Compose of nodes/units connected by links Each link has a numeric

More information

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

Natural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu Natural Language Processing CS 6320 Lecture 6 Neural Language Models Instructor: Sanda Harabagiu In this lecture We shall cover: Deep Neural Models for Natural Language Processing Introduce Feed Forward

More information

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

Artificial neural networks are the paradigm of connectionist systems (connectionism vs. symbolism) Artificial Neural Networks Analogy to biological neural systems, the most robust learning systems we know. Attempt to: Understand natural biological systems through computational modeling. Model intelligent

More information

Supervised Learning with Neural Networks. We now look at how an agent might learn to solve a general problem by seeing examples.

Supervised Learning with Neural Networks. We now look at how an agent might learn to solve a general problem by seeing examples. Supervised Learning with Neural Networks We now look at how an agent might learn to solve a general problem by seeing examples. Aims: to present an outline of supervised learning as part of AI; to introduce

More information

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

Dr. Qadri Hamarsheh Supervised Learning in Neural Networks (Part 1) learning algorithm Δwkj wkj Theoretically practically Supervised Learning in Neural Networks (Part 1) A prescribed set of well-defined rules for the solution of a learning problem is called a learning algorithm. Variety of learning algorithms are existing,

More information

CT79 SOFT COMPUTING ALCCS-FEB 2014

CT79 SOFT COMPUTING ALCCS-FEB 2014 Q.1 a. Define Union, Intersection and complement operations of Fuzzy sets. For fuzzy sets A and B Figure Fuzzy sets A & B The union of two fuzzy sets A and B is a fuzzy set C, written as C=AUB or C=A OR

More information

Deep Learning for Computer Vision

Deep Learning for Computer Vision Deep Learning for Computer Vision Lecture 7: Universal Approximation Theorem, More Hidden Units, Multi-Class Classifiers, Softmax, and Regularization Peter Belhumeur Computer Science Columbia University

More information

Vulnerability of machine learning models to adversarial examples

Vulnerability of machine learning models to adversarial examples Vulnerability of machine learning models to adversarial examples Petra Vidnerová Institute of Computer Science The Czech Academy of Sciences Hora Informaticae 1 Outline Introduction Works on adversarial

More information

COMPUTATIONAL INTELLIGENCE

COMPUTATIONAL INTELLIGENCE COMPUTATIONAL INTELLIGENCE Fundamentals Adrian Horzyk Preface Before we can proceed to discuss specific complex methods we have to introduce basic concepts, principles, and models of computational intelligence

More information

WestminsterResearch

WestminsterResearch WestminsterResearch http://www.westminster.ac.uk/research/westminsterresearch Reinforcement learning in continuous state- and action-space Barry D. Nichols Faculty of Science and Technology This is an

More information

Neural Networks (Overview) Prof. Richard Zanibbi

Neural Networks (Overview) Prof. Richard Zanibbi Neural Networks (Overview) Prof. Richard Zanibbi Inspired by Biology Introduction But as used in pattern recognition research, have little relation with real neural systems (studied in neurology and neuroscience)

More information

Machine Learning for Software Engineering

Machine Learning for Software Engineering Machine Learning for Software Engineering Introduction and Motivation Prof. Dr.-Ing. Norbert Siegmund Intelligent Software Systems 1 2 Organizational Stuff Lectures: Tuesday 11:00 12:30 in room SR015 Cover

More information

Mini-project 2 CMPSCI 689 Spring 2015 Due: Tuesday, April 07, in class

Mini-project 2 CMPSCI 689 Spring 2015 Due: Tuesday, April 07, in class Mini-project 2 CMPSCI 689 Spring 2015 Due: Tuesday, April 07, in class Guidelines Submission. Submit a hardcopy of the report containing all the figures and printouts of code in class. For readability

More information

Data Mining. Neural Networks

Data Mining. Neural Networks Data Mining Neural Networks Goals for this Unit Basic understanding of Neural Networks and how they work Ability to use Neural Networks to solve real problems Understand when neural networks may be most

More information

Neural Bag-of-Features Learning

Neural Bag-of-Features Learning Neural Bag-of-Features Learning Nikolaos Passalis, Anastasios Tefas Department of Informatics, Aristotle University of Thessaloniki Thessaloniki 54124, Greece Tel,Fax: +30-2310996304 Abstract In this paper,

More information

Week 3: Perceptron and Multi-layer Perceptron

Week 3: Perceptron and Multi-layer Perceptron Week 3: Perceptron and Multi-layer Perceptron Phong Le, Willem Zuidema November 12, 2013 Last week we studied two famous biological neuron models, Fitzhugh-Nagumo model and Izhikevich model. This week,

More information

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

Assignment # 5. Farrukh Jabeen Due Date: November 2, Neural Networks: Backpropation Farrukh Jabeen Due Date: November 2, 2009. Neural Networks: Backpropation Assignment # 5 The "Backpropagation" method is one of the most popular methods of "learning" by a neural network. Read the class

More information

CHAPTER 6 HYBRID AI BASED IMAGE CLASSIFICATION TECHNIQUES

CHAPTER 6 HYBRID AI BASED IMAGE CLASSIFICATION TECHNIQUES CHAPTER 6 HYBRID AI BASED IMAGE CLASSIFICATION TECHNIQUES 6.1 INTRODUCTION The exploration of applications of ANN for image classification has yielded satisfactory results. But, the scope for improving

More information

The exam is closed book, closed notes except your one-page (two-sided) cheat sheet.

The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. CS 189 Spring 2015 Introduction to Machine Learning Final You have 2 hours 50 minutes for the exam. The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. No calculators or

More information

In this assignment, we investigated the use of neural networks for supervised classification

In this assignment, we investigated the use of neural networks for supervised classification Paul Couchman Fabien Imbault Ronan Tigreat Gorka Urchegui Tellechea Classification assignment (group 6) Image processing MSc Embedded Systems March 2003 Classification includes a broad range of decision-theoric

More information

Artificial Neural Networks Unsupervised learning: SOM

Artificial Neural Networks Unsupervised learning: SOM Artificial Neural Networks Unsupervised learning: SOM 01001110 01100101 01110101 01110010 01101111 01101110 01101111 01110110 01100001 00100000 01110011 01101011 01110101 01110000 01101001 01101110 01100001

More information

Kyrre Glette INF3490 Evolvable Hardware Cartesian Genetic Programming

Kyrre Glette INF3490 Evolvable Hardware Cartesian Genetic Programming Kyrre Glette kyrrehg@ifi INF3490 Evolvable Hardware Cartesian Genetic Programming Overview Introduction to Evolvable Hardware (EHW) Cartesian Genetic Programming Applications of EHW 3 Evolvable Hardware

More information

Neural Networks: What can a network represent. Deep Learning, Fall 2018

Neural Networks: What can a network represent. Deep Learning, Fall 2018 Neural Networks: What can a network represent Deep Learning, Fall 2018 1 Recap : Neural networks have taken over AI Tasks that are made possible by NNs, aka deep learning 2 Recap : NNets and the brain

More information

Supervised Learning in Neural Networks (Part 2)

Supervised Learning in Neural Networks (Part 2) Supervised Learning in Neural Networks (Part 2) Multilayer neural networks (back-propagation training algorithm) The input signals are propagated in a forward direction on a layer-bylayer basis. Learning

More information

Neural Networks: What can a network represent. Deep Learning, Spring 2018

Neural Networks: What can a network represent. Deep Learning, Spring 2018 Neural Networks: What can a network represent Deep Learning, Spring 2018 1 Recap : Neural networks have taken over AI Tasks that are made possible by NNs, aka deep learning 2 Recap : NNets and the brain

More information

Deep Learning. Volker Tresp Summer 2014

Deep Learning. Volker Tresp Summer 2014 Deep Learning Volker Tresp Summer 2014 1 Neural Network Winter and Revival While Machine Learning was flourishing, there was a Neural Network winter (late 1990 s until late 2000 s) Around 2010 there

More information

Solving the Traveling Salesman Problem using Reinforced Ant Colony Optimization techniques

Solving the Traveling Salesman Problem using Reinforced Ant Colony Optimization techniques Solving the Traveling Salesman Problem using Reinforced Ant Colony Optimization techniques N.N.Poddar 1, D. Kaur 2 1 Electrical Engineering and Computer Science, University of Toledo, Toledo, OH, USA 2

More information

1 Training/Validation/Testing

1 Training/Validation/Testing CPSC 340 Final (Fall 2015) Name: Student Number: Please enter your information above, turn off cellphones, space yourselves out throughout the room, and wait until the official start of the exam to begin.

More information

Fall 09, Homework 5

Fall 09, Homework 5 5-38 Fall 09, Homework 5 Due: Wednesday, November 8th, beginning of the class You can work in a group of up to two people. This group does not need to be the same group as for the other homeworks. You

More information

Lecture 20: Neural Networks for NLP. Zubin Pahuja

Lecture 20: Neural Networks for NLP. Zubin Pahuja Lecture 20: Neural Networks for NLP Zubin Pahuja zpahuja2@illinois.edu courses.engr.illinois.edu/cs447 CS447: Natural Language Processing 1 Today s Lecture Feed-forward neural networks as classifiers simple

More information

Module 1 Lecture Notes 2. Optimization Problem and Model Formulation

Module 1 Lecture Notes 2. Optimization Problem and Model Formulation Optimization Methods: Introduction and Basic concepts 1 Module 1 Lecture Notes 2 Optimization Problem and Model Formulation Introduction In the previous lecture we studied the evolution of optimization

More information

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016 CPSC 340: Machine Learning and Data Mining Principal Component Analysis Fall 2016 A2/Midterm: Admin Grades/solutions will be posted after class. Assignment 4: Posted, due November 14. Extra office hours:

More information

Simple Model Selection Cross Validation Regularization Neural Networks

Simple Model Selection Cross Validation Regularization Neural Networks Neural Nets: Many possible refs e.g., Mitchell Chapter 4 Simple Model Selection Cross Validation Regularization Neural Networks Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University February

More information

Support Vector Machines

Support Vector Machines Support Vector Machines RBF-networks Support Vector Machines Good Decision Boundary Optimization Problem Soft margin Hyperplane Non-linear Decision Boundary Kernel-Trick Approximation Accurancy Overtraining

More information

LECTURE 20: SWARM INTELLIGENCE 6 / ANT COLONY OPTIMIZATION 2

LECTURE 20: SWARM INTELLIGENCE 6 / ANT COLONY OPTIMIZATION 2 15-382 COLLECTIVE INTELLIGENCE - S18 LECTURE 20: SWARM INTELLIGENCE 6 / ANT COLONY OPTIMIZATION 2 INSTRUCTOR: GIANNI A. DI CARO ANT-ROUTING TABLE: COMBINING PHEROMONE AND HEURISTIC 2 STATE-TRANSITION:

More information

Artificial Neural Networks Lecture Notes Part 5. Stephen Lucci, PhD. Part 5

Artificial Neural Networks Lecture Notes Part 5. Stephen Lucci, PhD. Part 5 Artificial Neural Networks Lecture Notes Part 5 About this file: If you have trouble reading the contents of this file, or in case of transcription errors, email gi0062@bcmail.brooklyn.cuny.edu Acknowledgments:

More information

Deep (1) Matthieu Cord LIP6 / UPMC Paris 6

Deep (1) Matthieu Cord LIP6 / UPMC Paris 6 Deep (1) Matthieu Cord LIP6 / UPMC Paris 6 Syllabus 1. Whole traditional (old) visual recognition pipeline 2. Introduction to Neural Nets 3. Deep Nets for image classification To do : Voir la leçon inaugurale

More information

LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS

LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS Neural Networks Classifier Introduction INPUT: classification data, i.e. it contains an classification (class) attribute. WE also say that the class

More information

Argha Roy* Dept. of CSE Netaji Subhash Engg. College West Bengal, India.

Argha Roy* Dept. of CSE Netaji Subhash Engg. College West Bengal, India. Volume 3, Issue 3, March 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Training Artificial

More information

SIMULATION APPROACH OF CUTTING TOOL MOVEMENT USING ARTIFICIAL INTELLIGENCE METHOD

SIMULATION APPROACH OF CUTTING TOOL MOVEMENT USING ARTIFICIAL INTELLIGENCE METHOD Journal of Engineering Science and Technology Special Issue on 4th International Technical Conference 2014, June (2015) 35-44 School of Engineering, Taylor s University SIMULATION APPROACH OF CUTTING TOOL

More information

Dept. of Computing Science & Math

Dept. of Computing Science & Math Lecture 4: Multi-Laer Perceptrons 1 Revie of Gradient Descent Learning 1. The purpose of neural netor training is to minimize the output errors on a particular set of training data b adusting the netor

More information

CPSC 340: Machine Learning and Data Mining. More Linear Classifiers Fall 2017

CPSC 340: Machine Learning and Data Mining. More Linear Classifiers Fall 2017 CPSC 340: Machine Learning and Data Mining More Linear Classifiers Fall 2017 Admin Assignment 3: Due Friday of next week. Midterm: Can view your exam during instructor office hours next week, or after

More information

Local Search and Optimization Chapter 4. Mausam (Based on slides of Padhraic Smyth, Stuart Russell, Rao Kambhampati, Raj Rao, Dan Weld )

Local Search and Optimization Chapter 4. Mausam (Based on slides of Padhraic Smyth, Stuart Russell, Rao Kambhampati, Raj Rao, Dan Weld ) Local Search and Optimization Chapter 4 Mausam (Based on slides of Padhraic Smyth, Stuart Russell, Rao Kambhampati, Raj Rao, Dan Weld ) 1 2 Outline Local search techniques and optimization Hill-climbing

More information

Ant Colony Optimization: The Traveling Salesman Problem

Ant Colony Optimization: The Traveling Salesman Problem Ant Colony Optimization: The Traveling Salesman Problem Section 2.3 from Swarm Intelligence: From Natural to Artificial Systems by Bonabeau, Dorigo, and Theraulaz Andrew Compton Ian Rogers 12/4/2006 Traveling

More information

Image Compression: An Artificial Neural Network Approach

Image Compression: An Artificial Neural Network Approach Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and

More information

Machine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart

Machine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart Machine Learning The Breadth of ML Neural Networks & Deep Learning Marc Toussaint University of Stuttgart Duy Nguyen-Tuong Bosch Center for Artificial Intelligence Summer 2017 Neural Networks Consider

More information

Neural Network Neurons

Neural Network Neurons Neural Networks Neural Network Neurons 1 Receives n inputs (plus a bias term) Multiplies each input by its weight Applies activation function to the sum of results Outputs result Activation Functions Given

More information

Notes on Multilayer, Feedforward Neural Networks

Notes on Multilayer, Feedforward Neural Networks Notes on Multilayer, Feedforward Neural Networks CS425/528: Machine Learning Fall 2012 Prepared by: Lynne E. Parker [Material in these notes was gleaned from various sources, including E. Alpaydin s book

More information

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CHAPTER 4 CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS 4.1 Introduction Optical character recognition is one of

More information

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2017

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2017 CPSC 340: Machine Learning and Data Mining Principal Component Analysis Fall 2017 Assignment 3: 2 late days to hand in tonight. Admin Assignment 4: Due Friday of next week. Last Time: MAP Estimation MAP

More information

Theoretical Concepts of Machine Learning

Theoretical Concepts of Machine Learning Theoretical Concepts of Machine Learning Part 2 Institute of Bioinformatics Johannes Kepler University, Linz, Austria Outline 1 Introduction 2 Generalization Error 3 Maximum Likelihood 4 Noise Models 5

More information

Support Vector Machines

Support Vector Machines Support Vector Machines RBF-networks Support Vector Machines Good Decision Boundary Optimization Problem Soft margin Hyperplane Non-linear Decision Boundary Kernel-Trick Approximation Accurancy Overtraining

More information

METAHEURISTICS. Introduction. Introduction. Nature of metaheuristics. Local improvement procedure. Example: objective function

METAHEURISTICS. Introduction. Introduction. Nature of metaheuristics. Local improvement procedure. Example: objective function Introduction METAHEURISTICS Some problems are so complicated that are not possible to solve for an optimal solution. In these problems, it is still important to find a good feasible solution close to the

More information

ECG782: Multidimensional Digital Signal Processing

ECG782: Multidimensional Digital Signal Processing ECG782: Multidimensional Digital Signal Processing Object Recognition http://www.ee.unlv.edu/~b1morris/ecg782/ 2 Outline Knowledge Representation Statistical Pattern Recognition Neural Networks Boosting

More information

Machine Learning. Topic 5: Linear Discriminants. Bryan Pardo, EECS 349 Machine Learning, 2013

Machine Learning. Topic 5: Linear Discriminants. Bryan Pardo, EECS 349 Machine Learning, 2013 Machine Learning Topic 5: Linear Discriminants Bryan Pardo, EECS 349 Machine Learning, 2013 Thanks to Mark Cartwright for his extensive contributions to these slides Thanks to Alpaydin, Bishop, and Duda/Hart/Stork

More information

Neural Nets for Adaptive Filter and Adaptive Pattern Recognition

Neural Nets for Adaptive Filter and Adaptive Pattern Recognition Adaptive Pattern btyoung@gmail.com CSCE 636 10 February 2010 Outline Adaptive Combiners and Filters Minimal Disturbance and the Algorithm Madaline Rule II () Published 1988 in IEEE Journals Bernard Widrow

More information

Machine Learning Classifiers and Boosting

Machine Learning Classifiers and Boosting Machine Learning Classifiers and Boosting Reading Ch 18.6-18.12, 20.1-20.3.2 Outline Different types of learning problems Different types of learning algorithms Supervised learning Decision trees Naïve

More information

Perceptron: This is convolution!

Perceptron: This is convolution! Perceptron: This is convolution! v v v Shared weights v Filter = local perceptron. Also called kernel. By pooling responses at different locations, we gain robustness to the exact spatial location of image

More information

More on Neural Networks. Read Chapter 5 in the text by Bishop, except omit Sections 5.3.3, 5.3.4, 5.4, 5.5.4, 5.5.5, 5.5.6, 5.5.7, and 5.

More on Neural Networks. Read Chapter 5 in the text by Bishop, except omit Sections 5.3.3, 5.3.4, 5.4, 5.5.4, 5.5.5, 5.5.6, 5.5.7, and 5. More on Neural Networks Read Chapter 5 in the text by Bishop, except omit Sections 5.3.3, 5.3.4, 5.4, 5.5.4, 5.5.5, 5.5.6, 5.5.7, and 5.6 Recall the MLP Training Example From Last Lecture log likelihood

More information

Neural Network Optimization and Tuning / Spring 2018 / Recitation 3

Neural Network Optimization and Tuning / Spring 2018 / Recitation 3 Neural Network Optimization and Tuning 11-785 / Spring 2018 / Recitation 3 1 Logistics You will work through a Jupyter notebook that contains sample and starter code with explanations and comments throughout.

More information

Radial Basis Function Networks: Algorithms

Radial Basis Function Networks: Algorithms Radial Basis Function Networks: Algorithms Neural Computation : Lecture 14 John A. Bullinaria, 2015 1. The RBF Mapping 2. The RBF Network Architecture 3. Computational Power of RBF Networks 4. Training

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: (jpineau@cs.mcgill.ca) Class web page: www.cs.mcgill.ca/~jpineau/comp551 Unless otherwise noted, all material posted for this course

More information

CIS581: Computer Vision and Computational Photography Project 4, Part B: Convolutional Neural Networks (CNNs) Due: Dec.11, 2017 at 11:59 pm

CIS581: Computer Vision and Computational Photography Project 4, Part B: Convolutional Neural Networks (CNNs) Due: Dec.11, 2017 at 11:59 pm CIS581: Computer Vision and Computational Photography Project 4, Part B: Convolutional Neural Networks (CNNs) Due: Dec.11, 2017 at 11:59 pm Instructions CNNs is a team project. The maximum size of a team

More information

CPSC 340: Machine Learning and Data Mining. Logistic Regression Fall 2016

CPSC 340: Machine Learning and Data Mining. Logistic Regression Fall 2016 CPSC 340: Machine Learning and Data Mining Logistic Regression Fall 2016 Admin Assignment 1: Marks visible on UBC Connect. Assignment 2: Solution posted after class. Assignment 3: Due Wednesday (at any

More information

Pattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition

Pattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition Pattern Recognition Kjell Elenius Speech, Music and Hearing KTH March 29, 2007 Speech recognition 2007 1 Ch 4. Pattern Recognition 1(3) Bayes Decision Theory Minimum-Error-Rate Decision Rules Discriminant

More information

Classification: Linear Discriminant Functions

Classification: Linear Discriminant Functions Classification: Linear Discriminant Functions CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Discriminant functions Linear Discriminant functions

More information

Final Exam. Introduction to Artificial Intelligence. CS 188 Spring 2010 INSTRUCTIONS. You have 3 hours.

Final Exam. Introduction to Artificial Intelligence. CS 188 Spring 2010 INSTRUCTIONS. You have 3 hours. CS 188 Spring 2010 Introduction to Artificial Intelligence Final Exam INSTRUCTIONS You have 3 hours. The exam is closed book, closed notes except a two-page crib sheet. Please use non-programmable calculators

More information

Lecture 13. Deep Belief Networks. Michael Picheny, Bhuvana Ramabhadran, Stanley F. Chen

Lecture 13. Deep Belief Networks. Michael Picheny, Bhuvana Ramabhadran, Stanley F. Chen Lecture 13 Deep Belief Networks Michael Picheny, Bhuvana Ramabhadran, Stanley F. Chen IBM T.J. Watson Research Center Yorktown Heights, New York, USA {picheny,bhuvana,stanchen}@us.ibm.com 12 December 2012

More information

PARTICLE SWARM OPTIMIZATION (PSO)

PARTICLE SWARM OPTIMIZATION (PSO) PARTICLE SWARM OPTIMIZATION (PSO) J. Kennedy and R. Eberhart, Particle Swarm Optimization. Proceedings of the Fourth IEEE Int. Conference on Neural Networks, 1995. A population based optimization technique

More information

10-701/15-781, Fall 2006, Final

10-701/15-781, Fall 2006, Final -7/-78, Fall 6, Final Dec, :pm-8:pm There are 9 questions in this exam ( pages including this cover sheet). If you need more room to work out your answer to a question, use the back of the page and clearly

More information

Training of Neural Networks. Q.J. Zhang, Carleton University

Training of Neural Networks. Q.J. Zhang, Carleton University Training of Neural Networks Notation: x: input of the original modeling problem or the neural network y: output of the original modeling problem or the neural network w: internal weights/parameters of

More information

Optimal Power Flow Using Particle Swarm Optimization

Optimal Power Flow Using Particle Swarm Optimization Optimal Power Flow Using Particle Swarm Optimization M.Chiranjivi, (Ph.D) Lecturer Department of ECE Bule Hora University, Bulehora, Ethiopia. Abstract: The Optimal Power Flow (OPF) is an important criterion

More information

Local Search and Optimization Chapter 4. Mausam (Based on slides of Padhraic Smyth, Stuart Russell, Rao Kambhampati, Raj Rao, Dan Weld )

Local Search and Optimization Chapter 4. Mausam (Based on slides of Padhraic Smyth, Stuart Russell, Rao Kambhampati, Raj Rao, Dan Weld ) Local Search and Optimization Chapter 4 Mausam (Based on slides of Padhraic Smyth, Stuart Russell, Rao Kambhampati, Raj Rao, Dan Weld ) 1 2 Outline Local search techniques and optimization Hill-climbing

More information

2. Neural network basics

2. Neural network basics 2. Neural network basics Next commonalities among different neural networks are discussed in order to get started and show which structural parts or concepts appear in almost all networks. It is presented

More information

A *69>H>N6 #DJGC6A DG C<>C::G>C<,8>:C8:H /DA 'D 2:6G, ()-"&"3 -"(' ( +-" " " % '.+ % ' -0(+$,

A *69>H>N6 #DJGC6A DG C<>C::G>C<,8>:C8:H /DA 'D 2:6G, ()-&3 -(' ( +-   % '.+ % ' -0(+$, The structure is a very important aspect in neural network design, it is not only impossible to determine an optimal structure for a given problem, it is even impossible to prove that a given structure

More information

More on Learning. Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization

More on Learning. Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization More on Learning Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization Neural Net Learning Motivated by studies of the brain. A network of artificial

More information

DEEP LEARNING REVIEW. Yann LeCun, Yoshua Bengio & Geoffrey Hinton Nature Presented by Divya Chitimalla

DEEP LEARNING REVIEW. Yann LeCun, Yoshua Bengio & Geoffrey Hinton Nature Presented by Divya Chitimalla DEEP LEARNING REVIEW Yann LeCun, Yoshua Bengio & Geoffrey Hinton Nature 2015 -Presented by Divya Chitimalla What is deep learning Deep learning allows computational models that are composed of multiple

More information

Clustering with Reinforcement Learning

Clustering with Reinforcement Learning Clustering with Reinforcement Learning Wesam Barbakh and Colin Fyfe, The University of Paisley, Scotland. email:wesam.barbakh,colin.fyfe@paisley.ac.uk Abstract We show how a previously derived method of

More information

CSEP 573: Artificial Intelligence

CSEP 573: Artificial Intelligence CSEP 573: Artificial Intelligence Machine Learning: Perceptron Ali Farhadi Many slides over the course adapted from Luke Zettlemoyer and Dan Klein. 1 Generative vs. Discriminative Generative classifiers:

More information

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

Linear Models. Lecture Outline: Numeric Prediction: Linear Regression. Linear Classification. The Perceptron. Support Vector Machines Linear Models Lecture Outline: Numeric Prediction: Linear Regression Linear Classification The Perceptron Support Vector Machines Reading: Chapter 4.6 Witten and Frank, 2nd ed. Chapter 4 of Mitchell Solving

More information

Pre-requisite Material for Course Heuristics and Approximation Algorithms

Pre-requisite Material for Course Heuristics and Approximation Algorithms Pre-requisite Material for Course Heuristics and Approximation Algorithms This document contains an overview of the basic concepts that are needed in preparation to participate in the course. In addition,

More information

LECTURE 16: SWARM INTELLIGENCE 2 / PARTICLE SWARM OPTIMIZATION 2

LECTURE 16: SWARM INTELLIGENCE 2 / PARTICLE SWARM OPTIMIZATION 2 15-382 COLLECTIVE INTELLIGENCE - S18 LECTURE 16: SWARM INTELLIGENCE 2 / PARTICLE SWARM OPTIMIZATION 2 INSTRUCTOR: GIANNI A. DI CARO BACKGROUND: REYNOLDS BOIDS Reynolds created a model of coordinated animal

More information

Ant Colony Optimization

Ant Colony Optimization Ant Colony Optimization CompSci 760 Patricia J Riddle 1 Natural Inspiration The name Ant Colony Optimization was chosen to reflect its original inspiration: the foraging behavior of some ant species. It

More information

FAST NEURAL NETWORK ALGORITHM FOR SOLVING CLASSIFICATION TASKS

FAST NEURAL NETWORK ALGORITHM FOR SOLVING CLASSIFICATION TASKS Virginia Commonwealth University VCU Scholars Compass Theses and Dissertations Graduate School 2012 FAST NEURAL NETWORK ALGORITHM FOR SOLVING CLASSIFICATION TASKS Noor Albarakati Virginia Commonwealth

More information

Deep Neural Networks Optimization

Deep Neural Networks Optimization Deep Neural Networks Optimization Creative Commons (cc) by Akritasa http://arxiv.org/pdf/1406.2572.pdf Slides from Geoffrey Hinton CSC411/2515: Machine Learning and Data Mining, Winter 2018 Michael Guerzhoy

More information

How Learning Differs from Optimization. Sargur N. Srihari

How Learning Differs from Optimization. Sargur N. Srihari How Learning Differs from Optimization Sargur N. srihari@cedar.buffalo.edu 1 Topics in Optimization Optimization for Training Deep Models: Overview How learning differs from optimization Risk, empirical

More information

Programming Exercise 3: Multi-class Classification and Neural Networks

Programming Exercise 3: Multi-class Classification and Neural Networks Programming Exercise 3: Multi-class Classification and Neural Networks Machine Learning Introduction In this exercise, you will implement one-vs-all logistic regression and neural networks to recognize

More information

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

Function approximation using RBF network. 10 basis functions and 25 data points. 1 Function approximation using RBF network F (x j ) = m 1 w i ϕ( x j t i ) i=1 j = 1... N, m 1 = 10, N = 25 10 basis functions and 25 data points. Basis function centers are plotted with circles and data

More information

Mutations for Permutations

Mutations for Permutations Mutations for Permutations Insert mutation: Pick two allele values at random Move the second to follow the first, shifting the rest along to accommodate Note: this preserves most of the order and adjacency

More information

Neural Network Weight Selection Using Genetic Algorithms

Neural Network Weight Selection Using Genetic Algorithms Neural Network Weight Selection Using Genetic Algorithms David Montana presented by: Carl Fink, Hongyi Chen, Jack Cheng, Xinglong Li, Bruce Lin, Chongjie Zhang April 12, 2005 1 Neural Networks Neural networks

More information

Heuristic Search Methodologies

Heuristic Search Methodologies Linköping University January 11, 2016 Department of Science and Technology Heuristic Search Methodologies Report on the implementation of a heuristic algorithm Name E-mail Joen Dahlberg joen.dahlberg@liu.se

More information

IN recent years, neural networks have attracted considerable attention

IN recent years, neural networks have attracted considerable attention Multilayer Perceptron: Architecture Optimization and Training Hassan Ramchoun, Mohammed Amine Janati Idrissi, Youssef Ghanou, Mohamed Ettaouil Modeling and Scientific Computing Laboratory, Faculty of Science

More information

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction Akarsh Pokkunuru EECS Department 03-16-2017 Contractive Auto-Encoders: Explicit Invariance During Feature Extraction 1 AGENDA Introduction to Auto-encoders Types of Auto-encoders Analysis of different

More information

Exercise: Training Simple MLP by Backpropagation. Using Netlab.

Exercise: Training Simple MLP by Backpropagation. Using Netlab. Exercise: Training Simple MLP by Backpropagation. Using Netlab. Petr Pošík December, 27 File list This document is an explanation text to the following script: demomlpklin.m script implementing the beckpropagation

More information