Goto

Collaborating Authors

 Industry


In Search of the Horowitz Factor

AI Magazine

The article introduces the reader to a large interdisciplinary research project whose goal is to use AI to gain new insight into a complex artistic phenomenon. We study fundamental principles of expressive music performance by measuring performance aspects in large numbers of recordings by highly skilled musicians (concert pianists) and analyzing the data with state-of-the-art methods from areas such as machine learning, data mining, and data visualization. The article first introduces the general research questions that guide the project and then summarizes some of the most important results achieved to date, with an emphasis on the most recent and still rather speculative work. A broad view of the discovery process is given, from data acquisition through data visualization to inductive model building and pattern discovery, and it turns out that AI plays an important role in all stages of such an ambitious enterprise. Our current results show that it is possible for machines to make novel and interesting discoveries even in a domain such as music and that even if we might never find the "Horowitz Factor," AI can give us completely new insights into complex artistic behavior.


AI in the News

AI Magazine

July 7, 2003 culture…with this view that technology order to build a better kindergartner, we (www.thewesterlysun.com). "The Westerly eventually will destroy us,' said Dan don't seem as fazed by the idea of reprogramming Public Library and The Westerly Hospital Sandin, director of the Electronic Visual-ourselves into something beyond are cosponsoring a video and discussion Are keep in mind that (1) the mere mention of July 15: Robotics. Matrix Reloaded likely won't be the last reflect the overall tenor of the article; (3) although by developing artificial intelligence Steven good last forever; and (4) the AI in the News Tin Woman might really be so bad after Levy. "There's a archived--can be found by going to scary lesson in these contests between the www.aaai.org/aitopics/html/current.html. "Set in the not-too-distant species, one that gets smarter and more independent'Socrates was against it computer would ever beat a human chess Networking Technologies for the Information because he thought people would become champion. 'Neural implants for Parkinson's and computers get smarter, is it (disease) didn't exist four years ago. Pick an answer: *I think it is have computers powerful enough to emulate (www.wired.com). If you're the human brain, that was considered potentially rabid robots and other supposedly like 46 percent of the people who were very speculative. Now if you talk to sentient technology is exactly what asked this question at Blockbuster's Web mainstream experts, they say of course motivated ArtBots' organizers to host the site, you'll respond, 'It could happen.' If there will be three-dimensional molecular show, which brought together 23 robots you're worrying that this puts you in the circuits in about a decade.'"


Representing and Aggregating Conflicting Beliefs

Journal of Artificial Intelligence Research

We consider the two-fold problem of representing collective beliefs and aggregating these beliefs. We propose a novel representation for collective beliefs that uses modular, transitive relations over possible worlds. They allow us to represent conflicting opinions and they have a clear semantics, thus improving upon the quasi-transitive relations often used in social choice. We then describe a way to construct the belief state of an agent informed by a set of sources of varying degrees of reliability. This construction circumvents Arrow's Impossibility Theorem in a satisfactory manner by accounting for the explicitly encoded conflicts. We give a simple set-theory-based operator for combining the information of multiple agents. We show that this operator satisfies the desirable invariants of idempotence, commutativity, and associativity, and, thus, is well-behaved when iterated, and we describe a computationally effective way of computing the resulting belief state. Finally, we extend our framework to incorporate voting.


Decision-Theoretic Bidding Based on Learned Density Models in Simultaneous, Interacting Auctions

Journal of Artificial Intelligence Research

Auctions are becoming an increasingly popular method for transacting business, especially over the Internet. This article presents a general approach to building autonomous bidding agents to bid in multiple simultaneous auctions for interacting goods. A core component of our approach learns a model of the empirical price dynamics based on past data and uses the model to analytically calculate, to the greatest extent possible, optimal bids. We introduce a new and general boosting-based algorithm for conditional density estimation problems of this kind, i.e., supervised learning problems in which the goal is to estimate the entire conditional distribution of the real-valued label. This approach is fully implemented as ATTac-2001, a top-scoring agent in the second Trading Agent Competition (TAC-01). We present experiments demonstrating the effectiveness of our boosting-based price predictor relative to several reasonable alternatives.


Ensembles of Protein Molecules as Statistical Analog Computers

arXiv.org Artificial Intelligence

A class of analog computers built from large numbers of microscopic probabilistic machines is discussed. It is postulated that such computers are implemented in biological systems as ensembles of protein molecules. The formalism is based on an abstract computational model referred to as Protein Molecule Machine (PMM). A PMM is a continuous-time first-order Markov system with real input and output vectors, a finite set of discrete states, and the input-dependent conditional probability densities of state transitions. The output of a PMM is a function of its input and state. The components of input vector, called generalized potentials, can be interpreted as membrane potential, and concentrations of neurotransmitters. The components of output vector, called generalized currents, can represent ion currents, and the flows of second messengers. An Ensemble of PMMs (EPMM) is a set of independent identical PMMs with the same input vector, and the output vector equal to the sum of output vectors of individual PMMs. The paper suggests that biological neurons have much more sophisticated computational resources than the presently popular models of artificial neurons.


Answer Set Planning Under Action Costs

Journal of Artificial Intelligence Research

Recently, planning based on answer set programming has been proposed as an approach towards realizing declarative planning systems. In this paper, we present the language Kc, which extends the declarative planning language K by action costs. Kc provides the notion of admissible and optimal plans, which are plans whose overall action costs are within a given limit resp. minimum over all plans (i.e., cheapest plans). As we demonstrate, this novel language allows for expressing some nontrivial planning tasks in a declarative way. Furthermore, it can be utilized for representing planning problems under other optimality criteria, such as computing ``shortest'' plans (with the least number of steps), and refinement combinations of cheapest and fastest plans. We study complexity aspects of the language Kc and provide a transformation to logic programs, such that planning problems are solved via answer set programming. Furthermore, we report experimental results on selected problems. Our experience is encouraging that answer set planning may be a valuable approach to expressive planning systems in which intricate planning problems can be naturally specified and solved.


Interval Constraint Solving for Camera Control and Motion Planning

arXiv.org Artificial Intelligence

Many problems in robust control and motion planning can be reduced to either find a sound approximation of the solution space determined by a set of nonlinear inequalities, or to the ``guaranteed tuning problem'' as defined by Jaulin and Walter, which amounts to finding a value for some tuning parameter such that a set of inequalities be verified for all the possible values of some perturbation vector. A classical approach to solve these problems, which satisfies the strong soundness requirement, involves some quantifier elimination procedure such as Collins' Cylindrical Algebraic Decomposition symbolic method. Sound numerical methods using interval arithmetic and local consistency enforcement to prune the search space are presented in this paper as much faster alternatives for both soundly solving systems of nonlinear inequalities, and addressing the guaranteed tuning problem whenever the perturbation vector has dimension one. The use of these methods in camera control is investigated, and experiments with the prototype of a declarative modeller to express camera motion using a cinematic language are reported and commented.


An Overview of RoboCup-2002 Fukuoka/Busan

AI Magazine

This article reports on the Sixth Robot World Cup Competition and Conference (RoboCup-2002) Fukuoka/Busan, which took place from 19 to 25 June in Fukuoka, Japan. It was the largest Robo- Cup since 1997 and held the first humanoid league competition in the world. Further, the first ROBOTREX (robot trade and exhibitions) was held with about 50 companies, universities, and institutes represented. To the best of our knowledge, this was the largest robotic event in history.


Toward RoboCup without Color Labeling

AI Magazine

To overcome these limitations, we propose an algorithm, called the CONTRACTING CURVE DENSITY (CCD) algorithm, for fitting parametric curves to image data. The method neither assumes object-specific color distributions, or specific edge profiles, nor does it need threshold parameters. To separate adjacent regions, we use local criteria that are based on local image statistics. We apply the method to the problem of localizing the ball and show that the CCD algorithm reliably localizes the ball even in the presence of heavily changing illumination, strong clutter, specularity, partial occlusion, and texture.


GRACE: An Autonomous Robot for the AAAI Robot Challenge

AI Magazine

In an attempt to solve as much of the AAAI Robot Challenge as possible, five research institutions representing academia, industry, and government integrated their research into a single robot named GRACE. This article describes this first-year effort by the GRACE team, including not only the various techniques each participant brought to GRACE but also the difficult integration effort itself.