The online incremental gradient (or backpropagation) algorithm is widely considered to be the fastest method for solving large-scale neural-network (NN) learning problems. In contrast, we show that an appropriately implemented iterative batch-mode (or block-mode) learning method can be much faster. For example, it is three times faster in the UCI letter classification problem (26 outputs, 16,000 data items, 6,066 parameters with a two-hidden-layer multilayer perceptron) and 353 times faster in a nonlinear regression problem arising in color recipe prediction (10 outputs, 1,000 data items, 2,210 parameters with a neuro-fuzzy modular network). The three principal innovative ingredients in our algorithm are the following: First, we use scaled trust-region regularization with inner-outer iteration to solve the associated "overdetermined" nonlinear least squares problem, where the inner iteration performs a truncated (or inexact) Newton method. Second, we employ Pearlmutter's implicit sparse Hessian matrix-vector multiply algorithm to construct the Krylov subspaces used to solve for the truncated Newton update. Third, we exploit sparsity (for preconditioning) in the matrices resulting from the NNs having many outputs.

We consider situations where training data is abundant and computing resources are comparatively scarce. We argue that suitably designed online learning algorithms asymptotically outperform any batch learning algorithm. Both theoretical and experimental evidences are presented.

In this paper we introduce a new underlying probabilistic model for principal component analysis (PCA). Our formulation interprets PCA as a particular Gaussian process prior on a mapping from a latent space to the observed data-space. We show that if the prior's covariance function constrains the mappings to be linear the model is equivalent to PCA, we then extend the model by considering less restrictive covariance functions which allow nonlinear mappings. This more general Gaussian process latent variable model (GPLVM) is then evaluated as an approach to the visualisation of high dimensional data for three different data-sets. Additionally our nonlinear algorithm can be further kernelised leading to'twin kernel PCA' in which a mapping between feature spaces occurs.

We present the software architecture of a robotic system for mapping abandoned mines. The software is capable of acquiring consistent 2D maps of large mines with many cycles, represented as Markov random £elds.

The design of cooperative multi-robot systems is a highly active research area in robotics. Two lines of research in particular have generated interest: the solution of large, weakly coupled MDPs, and the design and implementation of market architectures. We propose a new algorithm which joins together these two lines of research. For a class of coupled MDPs, our algorithm automatically designs a market architecture which causes a decentralized multi-robot system to converge to a consistent policy. We can show that this policy is the same as the one which would be produced by a particular centralized planning algorithm. We demonstrate the new algorithm on three simulation examples: multi-robot towing, multi-robot path planning with a limited fuel resource, and coordinating behaviors in a game of paint ball.

In this article, we present a novel approach to solving the localization problem in cellular networks. The goal is to estimate a mobile user's position, based on measurements of the signal strengths received from network base stations. Our solution works by building Gaussian process models for the distribution of signal strengths, as obtained in a series of calibration measurements. In the localization stage, the user's position can be estimated by maximizing the likelihood of received signal strengths with respect to the position. We investigate the accuracy of the proposed approach on data obtained within a large indoor cellular network.

In models that define probabilities via energies, maximum likelihood learning typically involves using Markov Chain Monte Carlo to sample from the model's distribution. If the Markov chain is started at the data distribution, learning often works well even if the chain is only run for a few time steps [3]. But if the data distribution contains modes separated by regions of very low density, brief MCMC will not ensure that different modes have the correct relative energies because it cannot move particles from one mode to another. We show how to improve brief MCMC by allowing long-range moves that are suggested by the data distribution. If the model is approximately correct, these long-range moves have a reasonable acceptance rate.

Gradient-following learning methods can encounter problems of implementation in many applications, and stochastic variants are frequently used to overcome these difficulties. We derive quantitative learning curves for three online training methods used with a linear perceptron: direct gradient descent, node perturbation, and weight perturbation. The maximum learning rate for the stochastic methods scales inversely with the first power of the dimensionality of the noise injected into the system; with sufficiently small learning rate, all three methods give identical learning curves. These results suggest guidelines for when these stochastic methods will be limited in their utility, and considerations for architectures in which they will be effective.

Mutual Boosting is a method aimed at incorporating contextual information to augment object detection. When multiple detectors of objects and parts are trained in parallel using AdaBoost [1], object detectors might use the remaining intermediate detectors to enrich the weak learner set. This method generalizes the efficient features suggested by Viola and Jones [2] thus enabling information inference between parts and objects in a compositional hierarchy. In our experiments eye-, nose-, mouth-and face detectors are trained using the Mutual Boosting framework. Results show that the method outperforms applications overlooking contextual information. We suggest that achieving contextual integration is a step toward humanlike detection capabilities.

There exist many different generalization error bounds for classification. Each of these bounds contains an improvement over the others for certain situations. Our goal is to combine these different improvements into a single bound. In particular we combine the PAC-Bayes approach introduced by McAllester [1], which is interesting for averaging classifiers, with the optimal union bound provided by the generic chaining technique developed by Fernique and Talagrand [2]. This combination is quite natural since the generic chaining is based on the notion of majorizing measures, which can be considered as priors on the set of classifiers, and such priors also arise in the PACbayesian setting.