Disaster rescue is one of the most serious social issues that involves very large numbers of heterogeneous agents in the hostile environment. The intention of the RoboCup Rescue project is to promote research and development in this socially significant domain at various levels, involving multiagent teamwork coordination, physical agents for search and rescue, information infrastructures, personal digital assistants, a standard simulator and decision-support systems, evaluation benchmarks for rescue strategies, and robotic systems that are all integrated into a comprehensive system in the future. For this effort, which was built on the success of the RoboCup Soccer project, we will provide forums of technical discussions and competitive evaluations for researchers and practitioners. Although the rescue domain is intuitively appealing as a large-scale multiagent and intelligent system domain, analysis has not yet revealed its domain characteristics. The first research evaluation meeting will be held at RoboCup-2001, in conjunction with the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-2001), as part of the RoboCup Rescue Simulation League and RoboCup/AAAI Rescue Robot Competition. In this article, we present a detailed analysis of the task domain and elucidate characteristics necessary for multiagent and intelligent systems for this domain. Then, we present an overview of the RoboCup Rescue project.

The Fourth Robotic Soccer World Championships (RoboCup-2000) was held from 27 August to 3 September 2000 at the Melbourne Exhibition Center in Melbourne, Australia. In total, 83 teams, consisting of about 500 people, participated in RoboCup-2000, and about 5000 spectators watched the events. RoboCup-2000 showed dramatic improvement over past years in each of the existing robotic soccer leagues (legged, small size, mid size, and simulation) and introduced RoboCup Jr. competitions and RoboCup Rescue and Humanoid demonstration events. The RoboCup Workshop, held in conjunction with the championships, provided a forum for the exchange of ideas and experiences among the different leagues. This article summarizes the advances seen at RoboCup-2000, including reports from the championship teams and overviews of all the RoboCup events.

We investigate the behavior of a Hebbian cell assembly of spiking neurons formed via a temporal synaptic learning curve. This learning function is based on recent experimental findings. It includes potentiation for short time delays between pre-and post-synaptic neuronal spiking, and depression for spiking events occuring in the reverse order. The coupling between the dynamics of the synaptic learning and of the neuronal activation leads to interesting results. We find that the cell assembly can fire asynchronously, but may also function in complete synchrony, or in distributed synchrony.

The reliability and accuracy of spike trains have been shown to depend on the nature of the stimulus that the neuron encodes.

We propose a new Markov Chain Monte Carlo algorithm which is a generalization of the stochastic dynamics method. The algorithm performs exploration of the state space using its intrinsic geometric structure, facilitating efficient sampling of complex distributions. Applied to Bayesian learning in neural networks, our algorithm was found to perform at least as well as the best state-of-the-art method while consuming considerably less time. 1 Introduction

This question was recently shown in [9] to be a special case of a much more fundamental problem: What are the features of the variable X that are relevant for the prediction of another, relevance, variable Y?

We describe a new incremental algorithm for training linear threshold functions: the Relaxed Online Maximum Margin Algorithm, or ROMMA. ROMMA can be viewed as an approximation to the algorithm that repeatedly chooses the hyperplane that classifies previously seen examples correctly with the maximum margin. It is known that such a maximum-margin hypothesis can be computed by minimizing the length of the weight vector subject to a number of linear constraints. ROMMA works by maintaining a relatively simple relaxation of these constraints that can be efficiently updated. We prove a mistake bound for ROMMA that is the same as that proved for the perceptron algorithm. Our analysis implies that the more computationally intensive maximum-margin algorithm also satisfies this mistake bound; this is the first worst-case performance guarantee for this algorithm. We describe some experiments using ROMMA and a variant that updates its hypothesis more aggressively as batch algorithms to recognize handwritten digits. The computational complexity and simplicity of these algorithms is similar to that of perceptron algorithm, but their generalization is much better. We describe a sense in which the performance of ROMMA converges to that of SVM in the limit if bias isn't considered.

The performance of regular and irregular Gallager-type errorcorrecting code is investigated via methods of statistical physics. The transmitted codeword comprises products of the original message bits selected by two randomly-constructed sparse matrices; the number of nonzero row/column elements in these matrices constitutes a family of codes. We show that Shannon's channel capacity may be saturated in equilibrium for many of the regular codes while slightly lower performance is obtained for others which may be of higher practical relevance. Decoding aspects are considered by employing the TAP approach which is identical to the commonly used belief-propagation-based decoding. We show that irregular codes may saturate Shannon's capacity but with improved dynamical properties. 1 Introduction The ever increasing information transmission in the modern world is based on reliably communicating messages through noisy transmission channels; these can be telephone lines, deep space, magnetic storing media etc. Error-correcting codes play a significant role in correcting errors incurred during transmission; this is carried out by encoding the message prior to transmission and decoding the corrupted received code-word for retrieving the original message.

Reinforcement learning in nonstationary environments is generally regarded as an important and yet difficult problem. This paper partially addresses the problem by formalizing a subclass of nonstationary environments. The environment model, called hidden-mode Markov decision process (HM-MDP), assumes that environmental changes are always confined to a small number of hidden modes.

In this paper, we consider the problem of active learning in trigonometric polynomial networks and give a necessary and sufficient condition of sample points to provide the optimal generalization capability. By analyzing the condition from the functional analytic point of view, we clarify the mechanism of achieving the optimal generalization capability. We also show that a set of training examples satisfying the condition does not only provide the optimal generalization but also reduces the computational complexity and memory required for the calculation of learning results. Finally, examples of sample points satisfying the condition are given and computer simulations are performed to demonstrate the effectiveness of the proposed active learning method.