Complexity theory of circuits strongly suggests that deep architectures can be much more efficient (sometimes exponentially) than shallow architectures, in terms of computational elements required to represent some functions. Deep multi-layer neural networks have many levels of non-linearities allowing them to compactly represent highly nonlinear and highly-varying functions. However, until recently it was not clear how to train such deep networks, since gradient-based optimization starting from random initialization appears to often get stuck in poor solutions.

Bob offers a face-detection web service where clients can submit their images for analysis. Alice would very much like to use the service, but is reluctant to reveal the content of her images to Bob. Bob, for his part, is reluctant to release his face detector, as he spent a lot of time, energy and money constructing it. Secure Multi-Party computations use cryptographic tools to solve this problem without leaking any information. Unfortunately, these methods are slow to compute and we introduce acouple of machine learning techniques that allow the parties to solve the problem while leaking a controlled amount of information. The first method is an information-bottleneck variant of AdaBoost that lets Bob find a subset of features that are enough for classifying an image patch, but not enough to actually reconstruct it.The second machine learning technique is active learning that allows Alice to construct an online classifier, based on a small number of calls to Bob's face detector. She can then use her online classifier as a fast rejector before using a cryptographically secure classifier on the remaining image patches.

We describe and analyze an algorithmic framework for online classification where each online trial consists of multiple prediction tasks that are tied together. We tackle the problem of updating the online hypothesis by defining a projection problem in which each prediction task corresponds to a single linear constraint. These constraints are tied together through a single slack parameter. We then introduce ageneral method for approximately solving the problem by projecting simultaneously and independently on each constraint which corresponds to a prediction sub-problem,and then averaging the individual solutions. We show that this approach constitutes a feasible, albeit not necessarily optimal, solution for the original projection problem. We derive concrete simultaneous projection schemes and analyze them in the mistake bound model. We demonstrate the power of the proposed algorithm in experiments with online multiclass text categorization. Our experiments indicate that a combination of class-dependent features with the simultaneous projection method outperforms previously studied algorithms.

Many problems that arise in machine learning domain deal with nonlinearity and quite often demand users to obtain global optimal solutions rather than local optimal ones. Optimization problems are inherent in machine learning algorithms and hence many methods in machine learning were inherited from the optimization literature. Popularly known as the initialization problem, the ideal set of parameters required will significantly depend on the given initialization values. The recently developed TRUST-TECH (TRansformation Under STability-reTaining Equilibria CHaracterization) methodology systematically explores the subspace of the parameters to obtain a complete set of local optimal solutions. In this thesis work, we propose TRUST-TECH based methods for solving several optimization and machine learning problems. Two stages namely, the local stage and the neighborhood-search stage, are repeated alternatively in the solution space to achieve improvements in the quality of the solutions. Our methods were tested on both synthetic and real datasets and the advantages of using this novel framework are clearly manifested. This framework not only reduces the sensitivity to initialization, but also allows the flexibility for the practitioners to use various global and local methods that work well for a particular problem of interest. Other hierarchical stochastic algorithms like evolutionary algorithms and smoothing algorithms are also studied and frameworks for combining these methods with TRUST-TECH have been proposed and evaluated on several test systems.

A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: We take a number of well known informal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. We believe that this equation formally captures the concept of machine intelligence in the broadest reasonable sense. We then show how this formal definition is related to the theory of universal optimal learning agents. Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines.

John McCarthy's contributions to computer science and artificial intelligence are legendary. He invented Lisp, made substantial contributions to early work in timesharing and the theory of computation, and was one of the founders of artificial intelligence and knowledge representation. This article, written in honor of McCarthy's 80th birthday, presents a brief biography, an overview of the major themes of his research, and a discussion of several of his major papers.

Multiagent Systems" was delivered by Mark W. Spong (University of Illinois (ICINCO 2007) "Toward Human-Machine Cooperation" was delivered by Patrick Millot (Université de Valenciennes, France), who is a renowned professor in Europe. ICINCO received 435 paper submissions, not including workshops, from more than 50 countries, in all continents. Sciences et Techniques de l'Ingénieur are researchers in one of the ICIN-and Robotics (ICINCO 2007) was The conference was also held in cooperation selected for poster presentation. The volume tracks: "Intelligent Control Systems will be published by Springer-Verlag. Autònoma de Barcelona, as a major international forum The two satellite workshops were Spain) and Janan Zaytoon (Centre de to debate technical and scientific the Third International Workshop on Recherche en Sciences et Technologies advances presented by researchers and Multiagent Robotic Systems (MARS de l'Information et de la Communication, developers both from academe and 2007), chaired by Joaquim Filipe, and Universite de Reims Champagne-industry.

Marvin Lee Minsky, a founder of the field of artificial intelligence and professor at MIT, celebrated his 80th birthday on August 9, 2007. This article seizes an opportune time to honor Marvin and his contributions and influence in artificial intelligence, science, and beyond. The article provides readers with some personal insights of Minsky from Danny Hillis, John McCarthy, Tom Mitchell, Erik Mueller, Doug Riecken, Aaron Sloman, and Patrick Henry Winston -- all members of the AI community that Minsky helped to found. The article continues with a brief resume of Minsky's research, which spans an enormous range of fields. It concludes with a short biographical account of Minsky's personal history.

Artificial Intelligence (IAAI-08) will be system.

This article presents some fundamental ideas about representing knowledge and dealing with meaning in computer representations. I will describe the issues as I currently understand them and describe how they came about, how they fit together, what problems they solve, and some of the things that the resulting framework can do. The ideas apply not just to graph-structured "node-and-link" representations, sometimes called semantic networks, but also to representations referred to variously as frames with slots, entities with relationships, objects with attributes, tables with columns, and records with fields and to the classes and variables of object-oriented data structures. I will start by describing some background experiences and thoughts that preceded the writing of my 1975 paper, "What's in a Link," which introduced many of these issues. After that, I will present some of the key ideas from that paper with a discussion of how some of those ideas have matured since then. Finally, I will describe some practical applications of these ideas in the context of knowledge access and information retrieval and will conclude with some thoughts about where I think we can go from here.