In multi-agent systems, individuals within a group coordinate and interact to achieve a goal.

Predictive state representations (PSRs) are a method of modeling dynamical systemsusing only observable data, such as actions and observations, to describe their model. PSRs use predictions about the outcome of future teststo summarize the system state.

We introduce a method to automatically improve character models for a handwritten script without the use of transcriptions and using a minimum of document specific training data. We show that we can use searches for the words in a dictionary to identify portions of the document whose transcriptions are unambiguous. Using templates extracted from those regions, we retrain our character prediction model to drastically improve our search retrieval performance for words in the document.

Humans are extremely adept at learning new skills by imitating the actions ofothers. A progression of imitative abilities has been observed in children, ranging from imitation of simple body movements to goalbased imitationbased on inferring intent. In this paper, we show that the problem of goal-based imitation can be formulated as one of inferring goals and selecting actions using a learned probabilistic graphical model of the environment. We first describe algorithms for planning actions to achieve a goal state using probabilistic inference. We then describe how planning can be used to bootstrap the learning of goal-dependent policies byutilizing feedback from the environment. The resulting graphical model is then shown to be powerful enough to allow goal-based imitation. Usinga simple maze navigation task, we illustrate how an agent can infer the goals of an observed teacher and imitate the teacher even when the goals are uncertain and the demonstration is incomplete.

Many real-world classification problems involve the prediction of multiple interdependent variables forming some structural dependency. Recentprogress in machine learning has mainly focused on supervised classification of such structured variables. In this paper, we investigate structured classification in a semi-supervised setting. We present a discriminative approach that utilizes the intrinsic geometry ofinput patterns revealed by unlabeled data points and we derive a maximum-margin formulation of semi-supervised learning for structured variables.

We consider the task of depth estimation from a single monocular image. Wetake a supervised learning approach to this problem, in which we begin by collecting a training set of monocular images (of unstructured outdoorenvironments which include forests, trees, buildings, etc.) and their corresponding ground-truth depthmaps. Then, we apply supervised learningto predict the depthmap as a function of the image. Depth estimation is a challenging problem, since local features alone are insufficient to estimate depth at a point, and one needs to consider the global context of the image. Our model uses a discriminatively-trained Markov Random Field (MRF) that incorporates multiscale local-and global-image features, and models both depths at individual points as well as the relation between depths at different points. We show that, even on unstructured scenes, our algorithm is frequently able to recover fairly accurate depthmaps.

MCMC offers no obvious way of approximating this wildly intractable sum [5, 8].

This paper describes a highly successful application of MRFs to the problem ofgenerating high-resolution range images. A new generation of range sensors combines the capture of low-resolution range images with the acquisition of registered high-resolution camera images. The MRF in this paper exploits the fact that discontinuities in range and coloring tend to co-align. This enables it to generate high-resolution, low-noise range images by integrating regular camera images into the range data. We show that by using such an MRF, we can substantially improve over existing range imaging technology.

Consider the problem of joint parameter estimation and prediction in a Markov random field: i.e., the model parameters are estimated on the basis of an initial setof data, and then the fitted model is used to perform prediction (e.g., smoothing, denoising, interpolation) on a new noisy observation. Working in the computation-limited setting, we analyze a joint method in which the same convex variational relaxation is used to construct an M-estimator for fitting parameters, and to perform approximate marginalization for the prediction step. The key result ofthis paper is that in the computation-limited setting, using an inconsistent parameter estimator (i.e., an estimator that returns the "wrong" model even in the infinite data limit) is provably beneficial, since the resulting errors can partially compensatefor errors made by using an approximate prediction technique. En route to this result, we analyze the asymptotic properties of M-estimators based on convex variational relaxations, and establish a Lipschitz stability property thatholds for a broad class of variational methods. We show that joint estimation/prediction basedon the reweighted sum-product algorithm substantially outperforms a commonly used heuristic based on ordinary sum-product.

A standard method to obtain stochastic models for symbolic time series is to train state-emitting hidden Markov models (SE-HMMs) with the Baum-Welch algorithm. Based on observable operator models (OOMs), in the last few months a number of novel learning algorithms for similar purposeshave been developed: (1,2) two versions of an "efficiency sharpening" (ES) algorithm, which iteratively improves the statistical efficiency ofa sequence of OOM estimators, (3) a constrained gradient descent ML estimator for transition-emitting HMMs (TE-HMMs). We give an overview on these algorithms and compare them with SE-HMM/EM learning on synthetic and real-life data.