Sebe, N., Cohen, I., Garg, A., Huang, T.S.

Machine Learning in Computer Vision

Series: Computational Imaging and Vision, Vol. 29
2005, XV, 242 p., Hardcover
ISBN: 1-4020-3274-9

About this book

The goal of this book is to address the use of several important machine learning techniques into computer vision applications. An innovative combination of computer vision and machine learning techniques has the promise of advancing the field of computer vision, which contributes to better understanding of complex real-world applications. The effective usage of machine learning technology in real-world computer vision problems requires understanding the domain of application, abstraction of a learning problem from a given computer vision task, and the selection of appropriate representations for the learnable (input) and learned (internal) entities of the system.

In this book, we address all these important aspects from a new perspective: that the key element in the current computer revolution is the use of machine learning to capture the variations in visual appearance, rather than having the designer of the model accomplish this. As a bonus, models learned from large datasets are likely to be more robust and more realistic than the brittle all-design models.

Table of contents

Foreword. Preface
1. INTRODUCTION. 1 Research Issues on Learning in Computer Vision. 2 Overview of the Book. 3 Contributions.
2. THEORY: PROBABILISTIC CLASSIFIERS. 1 Introduction. 2 Preliminaries and Notations. 3 Bayes Optimal Error and Entropy. 4 Analysis of Classification Error of Estimated (Mismatched)Distribution. 5 Density of Distributions. 6 Complex Probabilistic Models and Small Sample Effects. 7 Summary.
3. THEORY: GENERALIZATION BOUNDS. 1 Introduction. 2 Preliminaries. 3 A Margin Distribution Based Bound. 4 Analysis. 5 Summary.
4. THEORY: SEMI-SUPERVISED LEARNING. 1 Introduction.2 Properties of Classification. 3 Existing Literature. 4 Semi-supervised Learning Using Maximum Likelihood Estimation. 5 Asymptotic Properties of Maximum Likelihood Estimation with Labeled and Unlabeled Data. 6 Learning with Finite Data. 7 Concluding Remarks.
5. ALGORITHM: MAXIMUM LIKELIHOOD MINIMUM ENTROPY HMM. 1 Previous Work. 2 Mutual Information, Bayes Optimal Error, Entropy, and Conditional Probability. 3 Maximum Mutual Information HMMs. 4 Discussion. 5 Experimental Results. 6 Summary.
6. ALGORITHM: MARGIN DISTRIBUTION OPTIMIZATION. 1 Introduction. 2 A Margin Distribution Based Bound. 3 Existing Learning Algorithms. 4 The Margin Distribution Optimization (MDO) Algorithm. 5 Experimental Evaluation. 6 Conclusions. 7. ALGORITHM: LEARNING THE STRUCTURE OF BAYESIAN NETWORK CLASSIFIERS. 1 Introduction. 2 Bayesian Network Classifiers. 3 Switching between Models: Naive Bayes and TAN Classifiers. 4 Learning the Structure of Bayesian Network Classifiers: Existing Approaches. 5 Classification Driven Stochastic Structure Search. 6 Experiments. 7 Should Unlabeled Data Be Weighed Differently? 8 Active Learning. 9 Concluding Remarks.
8. APPLICATION: OFFICE ACTIVITY RECOGNITION. 1 Context-Sensitive Systems. 2 Towards Tractable and Robust Context Sensing. 3 Layered Hidden Markov Models (LHMMs). 4 Implementation of SEER. 5 Experiments. 6 Related Representations. 7 Summary.
9. APPLICATION: MULTIMODAL EVENT DETECTION. 1 Fusion Models: A Review. 2 A Hierarchical Fusion Model. 3 Experimental Setup, Features, and Results. 4 Summary.
10. APPLICATION: FACIAL EXPRESSION RECOGNITION. 1 Introduction. 2 Human Emotion Research. 3 Facial Expression Recognition System. 4 Experimental Analysis. 5 Discussion.
11. APPLICATION: BAYESIAN NETWORK CLASSIFIERS FOR FACE DETECTION. 1 Introduction. 2 Related Work. 3 Applying Bayesian Network Classifiers to Face Detection. 4 Experiments. 5 Discussion.
References. Index.

Kizza, Joseph M.

Computer Network Security

2005, XXII, 538 p. 115 illus., Hardcover
ISBN: 0-387-20473-3

About this textbook

A comprehensive survey of computer network security concepts, methods, and practices. This authoritative volume provides an optimal description of the principles and applications of computer network security in particular, and cyberspace security in general. The book is thematically divided into three segments: Part I describes the operation and security conditions surrounding computer networks; Part II builds from there and exposes readers to the prevailing security situation based on a constant security threat; and Part III - the core - presents readers with most of the best practices and solutions currently in use. It is intended as both a teaching tool and reference. This broad-ranging text/reference comprehensively surveys computer network security concepts, methods, and practices and covers network security tools, policies, and administrative goals in an integrated manner. It is an essential security resource for undergraduate or graduate study, practitioners in networks, and professionals who develop and maintain secure computer network systems.

Table of contents

Preface.- Part I : Understanding Computer Network Security.- Computer Network Fundamentals.- Understanding Network Security.- Part II: Security Challenges to Computer Networks.- Security Threats to Computer Networks.- Computer Network Vulnerabilities.- Cyber Crimes and Hackers.- Hostile Scripts.- Security Assessment, Analysis, and Assurance.- Part III: Dealing with Network Security Challenges.- Access Control and Authorization.-Authentication.- Cryptography.- Firewalls.- System Intrusion Detection and Prevention.- Computer and Network Forensics.- Virus and Content Filtering.- Security Evaluations of Computer Products.- Computer Network Security Protocols and Standards.- Security in Wireless Networks and Devices.- Other Efforts to Secure Information and Computer Networks.- Looking Ahead ? Security Beyond Computer Networks.- Part IV: Projects.- Projects.- Index.


Joseph Auslander et al.

Topology Proceedings Volume 28 Number 2 (2004)

Joseph Auslander
A group theoretic condition in topological dynamics

Valera Berestovskii and Conrad Plaut
The universal cover of the quotient of a locally defined group

A. Bouziad and J.-P. Troallic
Nonseparability and uniformities in topological groups

Timothy J. Carlson, Neil Hindman and Dona Strauss
The Graham-Rothschild Theorem and the algebra of \betaW

W. W. Comfort
Tampering with pseudocompact groups

W.W. Comfort and A.W. Hager
Maximal realcompact (and other) topologies

Szymon Dolecki
Elimination of covers in completeness

Jorge Galindo
Totally bounded group topologies that are Bohr topologies of LCA groups

Helge Glockner
Examples of differentiable mappings into non-locally convex spaces

Ivan Gotchev and Hristo Minchev
On sequential properties of Noetherian topological spaces

H. Hattab and E. Salhi
Groups of homeomorphisms and spectral topology

Salvador Hernandez
Extension of continuous functions on product spaces, Bohr compactification and almost periodic functions

Karl H. Hofmann and Sindey A. Morris
Lie theory and the structure of pro-Lie groups and pro-Lie algebras

Gerald Itzkowitz
Functional balance, discrete balance, and balance in topological groups

A. V. Karasev
The Urysohn identity for closed subsets of some nonmetrizable manifolds

Hisao Kato
Topological entropy of monotone maps and confluent maps on regular curves

Sabine Koppelberg
The Hales-Jewett theorem via retractions

Wieslaw Kubis and Arkady Leiderman
Semi-Eberlein spaces

Randall McCutcheon
Rhythmic functions and IP recurrence

Hector Mendez-Lango
The process of finding f' for an entire function f has infinite topological entropy

W.H. Previts and T.S. Wu
Notes on tidy subgroups of locally compact totally disconnected groups

Aleksandar Stojmirovic
Quasi-metric spaces with measure

Hideki Tsuiki
Dyadic subbases and efficiency properties of the induced {0, 1, ^}w-representations

Jan van Mill
A note on Ford's example

BiBTeX file of bibliographic information for this issue.


Edited by Lawrence K. Saul, Yair Weiss and Leon Bottou

Advances in Neural Information Processing Systems 17
Proceedings of the 2004 Conference

July 2005
ISBN 0-262-19534-8
7 x 10, 1696 pp.

The annual Neural Information Processing Systems (NIPS) conference is the flagship meeting on neural computation. It draws a diverse group of attendees -- physicists, neuroscientists, mathematicians, statisticians, and computer scientists. The presentations are interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, brain imaging, vision, speech and signal processing, reinforcement learning and control, emerging technologies, and applications. Only twenty-five percent of the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high. This volume contains the papers presented at the December, 2004 conference, held in Vancouver.

Lawrence K. Saul is Assistant Professor in the Department of Computer and Information Science at the University of Pennsylvania and General Chair of the 2004 NIPS conference.

Yair Weiss is Senior Lecturer in the School of Computer Science and Engineering at The Hebrew University of Jerusalem and Program Chair of the 2004 NIPS conference.

Leon Bottou is Senior Research Scientist at NEC Laboratories America in Princeton, New Jersey, and Publications Chair of the 2004 NIPS conference.

Kressner, Daniel

Numerical Methods for General and Structured Eigenvalue Problems

Series: Lecture Notes in Computational Science and Engineering, Vol. 46
2005, XIV, 258 p. 32 illus., Softcover
ISBN: 3-540-24546-4

About this book

This book is about computing eigenvalues, eigenvectors and invariant subspaces of matrices. The treatment includes generalized and structured eigenvalue problems, such as Hamiltonian or product eigenvalue problems. All vital aspects of eigenvalue computations are covered: theory, perturbation analysis, algorithms, high performance methodologies and software. The reader will learn about recently developed techniques which substantially improve the performance of some of the most widely numerical methods, the QR and the QZ algorithm as well as Krylov subspace methods. A unique feature of this book is the detailed treatment of structured eigenvalue problems, providing insight on accuracy and efficiency gains to be expected from algorithms that take the structure of a matrix into account.

Written for:

Computational scientists

Keywords:
computational methods
eigenvalue
matrix product
structured matrix