On large problems, reinforcement learning systems must use parameterized function approximators such as neural networks in order to generalize between similar situations and actions. In these cases there are no strong theoretical results on the accuracy of convergence, and computational results

Coupled biological and chemical systems, neural networks, social interacting species, the Internet and the World Wide Web, are only a few examples of systems composed by a large number of highly interconnected dynamical units. The first approach to capture the global properties of such systems

, in simulation, we demonstrate that the algorithm scales to large networks and handles real-world deployment geometries. Finally, we show how the algorithm supports localization of mobile nodes.

with sparse feature maps as appear for string kernels, allowing us to train a string kernel SVM on a 10 million real-world splice data set from computational biology. We integrated multiple kernel learning in our machine learning toolbox SHOGUN for which the source code is publicly available at

In this paper we present PEAS, a robust energyconserving protocol that can build long-lived, resilient sensor networks using a very large number of small sensors with short battery lifetime. PEAS extends the network lifetime by maintaining a necessary set of working nodes and turning o redundant

Dense subgraphs of sparse graphs (communities), which appear in most real-world complex networks, play an important role in many contexts. Computing them however is generally expensive. We propose here a measure of similarities between vertices based on random walks which has several important

ConceptNet is a freely available commonsense knowledgebase and natural-language-processing toolkit which supports many practical textual-reasoning tasks over real-world documents including topic-jisting (e.g. a news article containing the concepts, "gun," "convenience store

With the integration of cameras, mobile phones have evolved into networked personal image capture devices. Camera-phones can perform image processing tasks on the device itself and use the result as an additional means of user input and a source of context data. In this paper we present a system

Learning Bayesian networks is often cast as an optimization problem, where the computational task is to find a structure that maximizes a sta-tistically motivated score. By and large, existing learning tools address this optimization problem using standard heuristic search techniques. Since

Abstract Identifying meaningful community structure in social networks is a hard problem, and extreme network size or sparseness of the network compound the difficulty of the task. With a proliferation of real-world network datasets there has been an increasing demand for algorithms that work