Kumar Chellapilla

Bio: Kumar Chellapilla is an academic researcher from Microsoft. The author has contributed to research in topics: Evolutionary programming & Evolutionary algorithm. The author has an hindex of 35, co-authored 98 publications receiving 4819 citations. Previous affiliations of Kumar Chellapilla include University of California, San Diego & Villanova University.

High Performance Convolutional Neural Networks for Document Processing

Abstract: Convolutional neural networks (CNNs) are well known for producing state-of-the-art recognizers for document processing [1]. However, they can be difficult to implement and are usually slower than traditional multi-layer perceptrons (MLPs). We present three novel approaches to speeding up CNNs: a) unrolling convolution, b) using BLAS (basic linear algebra subroutines), and c) using GPUs (graphic processing units). Unrolled convolution converts the processing in each convolutional layer (both forward-propagation and back-propagation) into a matrix-matrix product. The matrix-matrix product representation of CNNs makes their implementation as easy as MLPs. BLAS is used to efficiently compute matrix products on the CPU. We also present a pixel shader based GPU implementation of CNNs. Results on character recognition problems indicate that unrolled convolution with BLAS produces a dramatic 2.4X−3.0X speedup. The GPU implementation is even faster and produces a 3.1X−4.1X speedup.

Using Machine Learning to Break Visual Human Interaction Proofs (HIPs)

Abstract: Machine learning is often used to automatically solve human tasks. In this paper, we look for tasks where machine learning algorithms are not as good as humans with the hope of gaining insight into their current limitations. We studied various Human Interactive Proofs (HIPs) on the market, because they are systems designed to tell computers and humans apart by posing challenges presumably too hard for computers. We found that most HIPs are pure recognition tasks which can easily be broken using machine learning. The harder HIPs use a combination of segmentation and recognition tasks. From this observation, we found that building segmentation tasks is the most effective way to confuse machine learning algorithms. This has enabled us to build effective HIPs (which we deployed in MSN Passport), as well as design challenging segmentation tasks for machine learning algorithms.

A scalable pattern mining approach to web graph compression with communities

Abstract: A link server is a system designed to support efficient implementations of graph computations on the web graph. In this work, we present a compression scheme for the web graph specifically designed to accommodate community queries and other random access algorithms on link servers. We use a frequent pattern mining approach to extract meaningful connectivity formations. Our Virtual Node Miner achieves graph compression without sacrificing random access by generating virtual nodes from frequent itemsets in vertex adjacency lists. The mining phase guarantees scalability by bounding the pattern mining complexity to O(E log E). We facilitate global mining, relaxing the requirement for the graph to be sorted by URL, enabling discovery for both inter-domain as well as intra-domain patterns. As a consequence, the approach allows incremental graph updates. Further, it not only facilitates but can also expedite graph computations such as PageRank and local random walks by implementing them directly on the compressed graph. We demonstrate the effectiveness of the proposed approach on several publicly available large web graph data sets. Experimental results indicate that the proposed algorithm achieves a 10- to 15-fold compression on most real word web graph data sets

Combining mutation operators in evolutionary programming

Abstract: Traditional investigations with evolutionary programming for continuous parameter optimization problems have used a single mutation operator with a parametrized probability density function (PDF), typically a Gaussian. Using a variety of mutation operators that can be combined during evolution to generate PDFs of varying shapes could hold the potential for producing better solutions with less computational effort. In view of this, a linear combination of Gaussian and Cauchy mutations is proposed. Simulations indicate that both the adaptive and nonadaptive versions of this operator are capable of producing solutions that are statistically as good as, or better, than those produced when using Gaussian or Cauchy mutations alone.

Designing human friendly human interaction proofs (HIPs)

Abstract: HIPs, or Human Interactive Proofs, are challenges meant to be easily solved by humans, while remaining too hard to be economically solved by computers. HIPs are increasingly used to protect services against automatic script attacks. To be effective, a HIP must be difficult enough to discourage script attacks by raising the computation and/or development cost of breaking the HIP to an unprofitable level. At the same time, the HIP must be easy enough to solve in order to not discourage humans from using the service. Early HIP designs have successfully met these criteria [1]. However, the growing sophistication of attackers and correspondingly increasing profit incentives have rendered most of the currently deployed HIPs vulnerable to attack [2,7,12]. Yet, most companies have been reluctant to increase the difficulty of their HIPs for fear of making them too complex or unappealing to humans. The purpose of this study is to find the visual distortions that are most effective at foiling computer attacks without hindering humans. The contribution of this research is that we discovered that 1) automatically generating HIPs by varying particular distortion parameters renders HIPs that are too easy for computer hackers to break, yet humans still have difficulty recognizing them, and 2) it is possible to build segmentation-based HIPs that are extremely difficult and expensive for computers to solve, while remaining relatively easy for humans.

Deep Learning

Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Evolutionary algorithms for solving multi-objective problems

Abstract: List of Figures. List of Tables. Preface. Foreword. 1. Basic Concepts. 2. Evolutionary Algorithm MOP Approaches. 3. MOEA Test Suites. 4. MOEA Testing and Analysis. 5. MOEA Theory and Issues. 3. MOEA Theoretical Issues. 6. Applications. 7. MOEA Parallelization. 8. Multi-Criteria Decision Making. 9. Special Topics. 10. Epilog. Appendix A: MOEA Classification and Technique Analysis. Appendix B: MOPs in the Literature. Appendix C: Ptrue & PFtrue for Selected Numeric MOPs. Appendix D: Ptrue & PFtrue for Side-Constrained MOPs. Appendix E: MOEA Software Availability. Appendix F: MOEA-Related Information. Index. References.

Cognitive Radio An Integrated Agent Architecture for Software Defined Radio

Abstract: An Integrated Agent Architecture for Software Defined Radio. Rapid-prototype cognitive radio, CR1, was developed to apply these.The modern software defined radio has been called the heart of a cognitive radio. Cognitive radio: an integrated agent architecture for software defined radio. Http:bwrc.eecs.berkeley.eduResearchMCMACR White paper final1.pdf. The cognitive radio, built on a software-defined radio, assumes. Radio: An Integrated Agent Architecture for Software Defined Radio, Ph.D. The need for software-defined radios is underlined and the most important notions used for such. Mitola III, Cognitive radio: an integrated agent architecture for software defined radio, Ph.D. This results in the set-theoretic ontology of radio knowledge defined in the. Cognitive Radio An Integrated Agent Architecture for Software.This article first briefly reviews the basic concepts about cognitive radio CR. Cognitive Radio-An Integrated Agent Architecture for Software Defined Radio. Cognitive Radio RHMZ 2007. Software-defined radio SDR idea 1. Cognitive radio: An integrated agent architecture for software.Cognitive Radio SOFTWARE DEFINED RADIO, AND ADAPTIVE WIRELESS SYSTEMS2 Cognitive Networks. 3 Joseph Mitola III, Cognitive Radio: An Integrated Agent Architecture for Software Defined Radio Stockholm.