Free Essay

Machine Learning

In: Computers and Technology

Submitted By arun20r
Words 663
Pages 3
Machine Learning

Neural Networks - II

12.4.3 Perceptron
Definition: It’s a step function based on a linear combination of real-valued inputs. If the combination is above a threshold it outputs a 1, otherwise it outputs a –1.

x1 x2

w1 w2 wn Σ w0 X0=1 {1 or –1}

xn

O(x1,x2,…,xn) = 1 if w0 + w1x1 + w2x2 + … + wnxn > 0 -1 otherwise
A perceptron draws a hyperplane as the decision boundary over the (n-dimensional) input space.

+ + + -

Decision boundary (WX = 0)

A perceptron can learn only examples that are called “linearly separable”. These are examples that can be perfectly separated by a hyperplane.

+ + + Linearly separable -

+ + + Non-linearly separable -

Perceptrons can learn many boolean functions: AND, OR, NAND, NOR, but not XOR However, every boolean function can be represented with a perceptron network that has two levels of depth or more. The weights of a perceptron implementing the AND function is shown below.

AND:

x1

W1=0.5 W2=0.5 Σ W0 = -0.8 X0=1

x2

12.4.3.1 Perceptron Learning
Learning a perceptron means finding the right values for W. The hypothesis space of a perceptron is the space of all weight vectors. The perceptron learning algorithm can be stated as below.

1. Assign random values to the weight vector 2. Apply the weight update rule to every training example 3. Are all training examples correctly classified? a. Yes. Quit b. No. Go back to Step 2. There are two popular weight update rules. i) The perceptron rule, and ii) Delta rule The Perceptron Rule For a new training example X = (x1, x2, …, xn), update each weight according to this rule: wi = wi + Δwi Where Δwi = η (t-o) xi t: target output o: output generated by the perceptron η: constant called the learning rate (e.g., 0.1) Comments about the perceptron training rule: • • • • If the example is correctly classified the term (t-o) equals zero, and no update on the weight is necessary. If the perceptron outputs –1 and the real answer is 1, the weight is increased. If the perceptron outputs a 1 and the real answer is -1, the weight is decreased. Provided the examples are linearly separable and a small value for η is used, the rule is proved to classify all training examples correctly (i.e, is consistent with the training data).

The Delta Rule What happens if the examples are not linearly separable? To address this situation we try to approximate the real concept using the delta rule. The key idea is to use a gradient descent search. We will try to minimize the following error: E = ½ Σi (ti – oi) 2 where the sum goes over all training examples. Here oi is the inner product WX and not sgn(WX) as with the perceptron rule. The idea is to find a minimum in the space of weights and the error function E.

The delta rule is as follows: For a new training example X = (x1, x2, …, xn), update each weight according to this rule: wi = wi + Δwi Where Δwi = -η E’(W)/wi η: learning rate (e.g., 0.1) It is easy to see that E’(W)/ wi = Σi (ti – oi) (-xi) So that gives us the following equation: wi = η Σi (ti – oi) xi There are two differences between the perceptron and the delta rule. The perceptron is based on an output from a step function, whereas the delta rule uses the linear combination of inputs directly. The perceptron is guaranteed to converge to a consistent hypothesis assuming the data is linearly separable. The delta rules converges in the limit but it does not need the condition of linearly separable data. There are two main difficulties with the gradient descent method: 1. 2. Convergence to a minimum may take a long time. There is no guarantee we will find the global minimum.

These are handled by using momentum terms and random perturbations to the weight vectors.

Similar Documents

Free Essay

Machine Learning

...Machine learning According to Alp Aydin (2010), Machine learning is an area of artificial intelligence that developed from design acknowledgment and computational learning hypothesis. It investigates the study and development of calculations that can gain from and make expectations on information. Such calculations work by building a model from sample inputs keeping in mind the end goal to settle on information driven forecasts or choices, as opposed to taking after entirely static project guidelines. Machine learning is firmly identified with computational statistics; a specialty that goes for the configuration of calculation for executing factual techniques on computers. It has solid ties to numerical enhancement, which conveys techniques, hypothesis and application areas to the field. Machine learning is utilized in a scope of registering errands where outlining and programming unequivocal calculations is in feasible (Marshland, 2009). Concepts of machine learning 1. Bayesian networks A Bayesian network is a probabilistic graphical model that speaks to an arrangement of irregular variables and their restrictive independencies through a coordinated non-cyclic chart. For instance, a Bayesian system could speak to the probabilistic connections between forex market and political unrests. Given the instances of political unrests, the system can be utilized to figure the probabilities of the forex market dropping. Proficient calculations exist that perform surmising and learning...

Words: 987 - Pages: 4

Free Essay

Machine Learning

...Foundations of Machine Learning Adaptive Computation and Machine Learning Thomas Dietterich, Editor Christopher Bishop, David Heckerman, Michael Jordan, and Michael Kearns, Associate Editors A complete list of books published in The Adaptive Computations and Machine Learning series appears at the back of this book. Foundations of Machine Learning Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar The MIT Press Cambridge, Massachusetts London, England c 2012 Massachusetts Institute of Technology All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means (including photocopying, recording, or information storage and retrieval) without permission in writing from the publisher. MIT Press books may be purchased at special quantity discounts for business or sales promotional use. For information, please email special sales@mitpress.mit.edu or write to Special Sales Department, The MIT Press, 55 Hayward Street, Cambridge, MA 02142. A This book was set in L TEX by the authors. Printed and bound in the United States of America. Library of Congress Cataloging-in-Publication Data Mohri, Mehryar. Foundations of machine learning / Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. p. cm. - (Adaptive computation and machine learning series) Includes bibliographical references and index. ISBN 978-0-262-01825-8 (hardcover : alk. paper) 1. Machine learning. 2. Computer algorithms. I. Rostamizadeh, Afshin. II...

Words: 137818 - Pages: 552

Premium Essay

Data Mining Practical Machine Learning Tools and Techniques - Weka

...Data Mining Practical Machine Learning Tools and Techniques The Morgan Kaufmann Series in Data Management Systems Series Editor: Jim Gray, Microsoft Research Data Mining: Practical Machine Learning Tools and Techniques, Second Edition Ian H. Witten and Eibe Frank Fuzzy Modeling and Genetic Algorithms for Data Mining and Exploration Earl Cox Data Modeling Essentials, Third Edition Graeme C. Simsion and Graham C. Witt Location-Based Services Jochen Schiller and Agnès Voisard Database Modeling with Microsoft® Visio for Enterprise Architects Terry Halpin, Ken Evans, Patrick Hallock, and Bill Maclean Designing Data-Intensive Web Applications Stefano Ceri, Piero Fraternali, Aldo Bongio, Marco Brambilla, Sara Comai, and Maristella Matera Mining the Web: Discovering Knowledge from Hypertext Data Soumen Chakrabarti Understanding SQL and Java Together: A Guide to SQLJ, JDBC, and Related Technologies Jim Melton and Andrew Eisenberg Database: Principles, Programming, and Performance, Second Edition Patrick O’Neil and Elizabeth O’Neil The Object Data Standard: ODMG 3.0 Edited by R. G. G. Cattell, Douglas K. Barry, Mark Berler, Jeff Eastman, David Jordan, Craig Russell, Olaf Schadow, Torsten Stanienda, and Fernando Velez Data on the Web: From Relations to Semistructured Data and XML Serge Abiteboul, Peter Buneman, and Dan Suciu Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations Ian H. Witten and Eibe Frank ...

Words: 191947 - Pages: 768

Free Essay

Machine Learning

...Task 1(Project: CS674) Mishra A.(Y6 Kumar D.(Y6152) Venkat(Y Introduction: The Pattern classification for given problem is posed with serious challenge as on one side the data set is highly imbalanced in favour of B+E against B(So we have to avoid over fitting for generalization) & on the other side wrong classification can have serious consequences in diplomatic relationship between nations. So Our thrust has been to choose between various methods , one with sound justification towards our results & showing how was it better than others . Based on comparative study of various methods we have finally chosen Biased Minimax Probability Machine [1] & we would be proving superiority of our methods over SVM classifier with different parameters which we tried. Besides authors [1] have shown superiority of BMPM over DT, Naive Bayesian Classifier, K-nn classification, & other under/over Sampling methods. Methodology of BMPM: For two class Classification: Let Family {x}, {y} with mean vector & Covariance matrices {x, ∑x }, {y, ∑y} belong to class1 & class2 respectively. Let α be the worst-case accuracy for future data points from family of {x}, and β be the worst-case accuracy for future data points from family of {y}. Depending upon severity of the false positive & true positive rates α, β(Policy variables) it tries to find a maximal hyper plane to separate the two classes [pic] [pic] We can also have Non Linear Classifier by mapping the feature space into suitable...

Words: 437 - Pages: 2

Premium Essay

The Pros And Cons Of Artificial Intelligence

...AI research is highly technical and specialized and is divided into subfields. John McCarthy, who coined the term in 1955, defines it as "the science and engineering of making intelligent machines”. AI research is divided by several technical issues. Some subfields focus on the solution of specific problems. Others focus on one of several possible approaches or on the use of a particular tool or towards the accomplishment of particular applications. Artificial intelligence is used for logistics, data mining, medical diagnosis and many other areas throughout the technology industry. The success was due to several factors: the increasing computational power of computers, a greater emphasis on solving specific sub problems, the creation of new...

Words: 833 - Pages: 4

Free Essay

Improving Assisted Technology

...With Machine Learning Techniques Senior Seminar in Computer Information Systems December 7, 2011 Abstract An ever increasing population of persons with learning disabilities are continually in need of better ways to overcome the unique challenges they face in today's modern, high communication world. While Assistive Technology is making strides to close the learning gap between persons with and without learning disabilities there is still a long way to go before technology provides a level playing field for these challenged individuals. Many of the issues with existing assistive technology revolves around clumsy, inefficient interfaces that struggle to find a balance between ease of use and sufficient complexity to ensure that the proper sequence of instructions is implemented. Machine learning is on the cutting edge of programming practices and presents some significant improvement possibilities in the areas of natural language processing, pattern recognition, and interface design. Machine learning has the potential to play a significant role in allowing assistive technologies to be more adaptive to persons with diverse sets of needs. This paper will attempt to define some specific areas of assistive technology that could benefit most from the application of machine learning. We will frame the definitions by aligning specific learning disabilities with current and future assistive technologies and then examining how the implementation of machine learning could...

Words: 2619 - Pages: 11

Free Essay

Iot and Beacons

...Privacy Snooper: IOT Arnab Kumar1 , Harishma Dayanidhi1 and Vijay Kumar KS1 {arnabk, hdayanid, vkanlanji}@andrew.cmu.edu 1 Carnegie Mellon School of Computer Science, Pittsburgh, USA Abstract. In various ML-as-a-service cloud systems, the process of performing machine learning over the data is almost treated as a black box, where the user just feeds in their data, knows the model used and the system outputs required insights. In this work, we explore the idea of being able to predict sensitive attributes associated with the database given that the adversary would have access to a few quasi-identifiers associated with the database. We use inversion attack as the theoretical foundation for our attack, and implement the same for our database. We experiment this attack for di↵erent variants of classification algorithms, like classification tree and regression tree. We follow it up with analysing the accuracy of our attack for each of our classification based machine learning algorithms for di↵erent size of training datasets. We end our work by trying to figure out what we say is the ”most impactful attribute”, by selectively removing the data pertaining to an attribute and check what is the corresponding e↵ect on inversion attack. We hope our work in this domain pushes future batches of this class to explore this question even further, and too look into understanding if Di↵erential Privacy solves this problem. Keywords: Inversion Attack, Black Box, Classification Tree...

Words: 5223 - Pages: 21

Free Essay

Assignment

...Active Learning with Support Vector Machines Kim Steenstrup Pedersen Department of Computer Science University of Copenhagen 2200 Copenhagen, Denmark kimstp@di.ku.dk Jan Kremer Department of Computer Science University of Copenhagen 2200 Copenhagen, Denmark jan.kremer@di.ku.dk Christian Igel Department of Computer Science University of Copenhagen 2200 Copenhagen, Denmark igel@di.ku.dk Abstract In machine learning, active learning refers to algorithms that autonomously select the data points from which they will learn. There are many data mining applications in which large amounts of unlabeled data are readily available, but labels (e.g., human annotations or results from complex experiments) are costly to obtain. In such scenarios, an active learning algorithm aims at identifying data points that, if labeled and used for training, would most improve the learned model. Labels are then obtained only for the most promising data points. This speeds up learning and reduces labeling costs. Support vector machine (SVM) classifiers are particularly well-suited for active learning due to their convenient mathematical properties. They perform linear classification, typically in a kernel-induced feature space, which makes measuring the distance of a data point from the decision boundary straightforward. Furthermore, heuristics can efficiently estimate how strongly learning from a data point influences the current model. This information can be used to actively...

Words: 9180 - Pages: 37

Free Essay

Bibliography

...Alazab, M., Layton, R., Venkataraman, S., Watters, P., 2010, Malware detection based on structural and behavioural features of api calls. Alrabaee, S., Saleem, N., Preda, S., Wang, L., Debbabi, M., 2014, OBA2: an Onion approach to binary code authorship attribution. Digital Investigation, 11, S94-S103. Anderson, R., Barton, C., Böhme, R., Clayton, R., Van Eeten, M. J., Levi, M., ... Savage, S., 2013, Measuring the cost of cybercrime. In The economics of information security and privacy (pp. 265-300). Springer Berlin Heidelberg. Androutsopoulos, Ion, et al., 2000, "Learning to filter spam e-mail: A comparison of a naive bayesian and a memory-based approach." arXiv preprint cs/0009009. Bagavandas, M., and Manimannan, G., 2008, Style consistency and authorship attribution: A statistical investigation*. Journal of Quantitative Linguistics 15.1: 100-110 Bishop, C. M., 2006, Pattern recognition and machine learning. springer. Bond, P., 2014, “Sony Hack: Activists to Drop ‘Interview’DVDs over North Korea via Balloon. The Hollywood Reporter, 16. Bouton, M. E., 2014, "Why behavior change is difficult to sustain." Preventive medicine 68: (p. 29-36) Brennan, M. R., Greenstadt, R. (2009, July). Practical Attacks Against Authorship Recognition Techniques. In IAAI. Brennan, M. R., and Greenstadt, R., 2009, Practical Attacks Against Authorship Recognition Techniques. IAAI. Brennan, M., Afroz, S., Greenstadt, R., 2012, Adversarial stylometry: Circumventing authorship recognition to...

Words: 1223 - Pages: 5

Free Essay

Artificial Intelligence

...friends and especially to the sisters in my dormitory who are always there for me in my ups and downs in life. You guys made my life extra special. Lastly, I give thanks to the Almighty God for being there for me. This project will never exist if you weren’t here for me. Gracias! Table of Contents I. Introduction 4 II. Computers, Robots, and Artificial Intelligence 5 a. Computer 6 b. Artificial Intelligence and Robots 7 III. Information Age and Information Society 8 a. Knowledge 9 b. Global mind 10 c. Global brain 11 IV. The Machine and the Machine of Mind 12 a. The Machines of Mind 13 b. The Most Human Mind of Machines 14 V. Conclusion 16 I. Introduction Artificial intelligence (AI) is an area of computer science that emphasizes the creation of intelligent machines that work and react like humans. Some of the activities computers with artificial intelligence are designed for include: speech recognition, learning, planning and problem solving. Artificial intelligence is a...

Words: 3551 - Pages: 15

Free Essay

What Can Information Technology Do for Law?

...CAN INFORMATION TECHNOLOGY DO FOR LAW? Johnathan Jenkins∗ TABLE OF CONTENTS I. INTRODUCTION ..............................................................................589 II. INCENTIVES FOR BETTER INTEGRATION OF INFORMATION TECHNOLOGY AND LAW ............................................................591 III. THE CURRENT STATE OF INFORMATION TECHNOLOGY IN LEGAL PRACTICE .......................................................................594 IV. THE DIRECTION OF LEGAL INFORMATICS: CURRENT RESEARCH .................................................................................597 A. Advances in Argumentation Models and Outcome Prediction ..............................................................................597 B. Machine Learning and Knowledge Discovery from Databases ..............................................................................600 C. Accessible, Structured Knowledge ...........................................602 V. INFORMATION TECHNOLOGY AND THE LEGAL PROFESSION: BARRIERS TO PROGRESS ......................................604 VI. CONCLUSION ..............................................................................607 I. INTRODUCTION MUCH CURRENT LEGAL WORK IS EMBARRASSINGLY, ABSURDLY, WASTEFUL. AI-RELATED TECHNOLOGY OFFERS GREAT PROMISE TO 1 IMPROVE THAT SITUATION. Many professionals now rely on information technology (“IT”) to simplify, automate, or better understand aspects of their work. Such software comes in varying degrees of...

Words: 9086 - Pages: 37

Free Essay

Resume

...education and experience to learn and contribute to a research position in the general area of machine learning, computer vision, and pattern recognition. Email: steve.krawczyk@gmail.com Website: www.stevekrawczyk.com EDUCATION Ph.D., Computer Science Michigan State University, East Lansing MI GPA 4.0 ADVISOR - Dr. Anil K. Jain THESIS - Video-based Face Recognition using 3D Models (Incomplete) Master of Science, Computer Science Michigan State University, East Lansing MI GPA 4.0 ADVISOR - Dr. Anil K. Jain THESIS - User Authentication using Online Signature and Speech Bachelor of Science, Computer Science Michigan State University, East Lansing MI COGNATE - Classic Literature and Arts August 2006 - December 2007 January 2003 - June 2005 GPA 3.56 August 1999 - December 2003 PROFESSIONAL EXPERIENCE SoarTech Senior AI Engineer Ann Arbor, MI September 2012 - Present • Design and implement algorithms related to expert systems, cognitive architectures, machine learning and machine vision. • Build algorithms designed to maximize situational awareness for controlling and monitoring multiple autonomous vehicles. • Integrate a verb learning and vision system with a ground robot; allow the robot to learn spacial relationships among specific targets and interact with the environment. Quantcast Senior Modeling Scientist San Francisco, CA May 2011 - September 2012 • Apply machine learning algorithms for directed advertising at very large scale using map reduce. • Optimize which...

Words: 805 - Pages: 4

Free Essay

Deep Learning Wikipedia

...Deep Learning more at http://ml.memect.com Contents 1 Artificial neural network 1 1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 History . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.2.1 Improvements since 2006 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.3.1 Network function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.3.2 Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3.3 Learning paradigms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3.4 Learning algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.4 Employing artificial neural networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.5 Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.5.1 Real-life applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.5.2 Neural networks and neuroscience . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.6 Neural network software ...

Words: 55759 - Pages: 224

Free Essay

Image Analysis of Radiograph​Ic Scans for Detection of Threats in Cargo Containers​

...identification and evaluation of cargo radiographic images having an extremely widespread and powerful impact for Homeland Security. Project Description Radiographic imaging has become an important tool for screening cargo containers for potential nuclear or radiological threats. We are investigating methods to extract features from these images that effectively characterize the contents and when combined with other measurements and information could indicate whether or not a threat is present. Analysis of single-energy radiographs is made particularly challenging by the large variety of cargo contents and the overall volume and mass of standard intermodel shipping containers. Once these features are extracted, we will leverage machine learning methodologies to perform threat detection utilizing these features along with other signature measurements and contextual information. The other...

Words: 2050 - Pages: 9

Free Essay

Student

...the probabilistic modeling of term frequency occurrences in documents. The fitted model can be used to estimate the similarity between documents as well as between a set of specified keywords using an additional layer of latent variables which are referred to as topics. The R package topicmodels provides basic infrastructure for fitting topic models based on data structures from the text mining package tm. The package includes interfaces to two algorithms for fitting topic models: the variational expectation-maximization algorithm provided by David M. Blei and co-authors and an algorithm using Gibbs sampling by Xuan-Hieu Phan and co-authors. Keywords: Gibbs sampling, R, text analysis, topic model, variational EM. 1. Introduction In machine learning and natural language processing topic models are generative models which provide a probabilistic framework for the term frequency occurrences in documents in a given corpus. Using only the term frequencies assumes that the information in which order the words occur in a document is negligible. This assumption is also referred to as the exchangeability assumption for the words in a document and this assumption leads to bag-of-words models. Topic models extend and build on classical methods in natural language processing such as the unigram model and the mixture of unigram models (Nigam, McCallum, Thrun, and Mitchell 2000) as well as Latent Semantic Analysis (LSA; Deerwester, Dumais, Furnas, Landauer, and Harshman 1990). Topic models...

Words: 6498 - Pages: 26