Theories of visual attention commonly posit that early parallel processes extract conspicuous featuressuch as color contrast and motion from the visual field. These features are then combined into a saliency map, and attention is directed to the most salient regions first. Top-down attentional control is achieved by modulating the contribution of different feature types to the saliency map. A key source of data concerning attentional control comes from behavioral studies in which the effect of recent experience is examined asindividuals repeatedly perform a perceptual discrimination task (e.g., "what shape is the odd-colored object?"). The robust finding is that repetition of features of recent trials (e.g., target color) facilitates performance. We view this facilitation as an adaptation to the statistical structure of the environment. We propose a probabilistic model of the environment that is updated after each trial. Under the assumption that attentional control operates so as to make performance more efficient for more likely environmental states, we obtain parsimonious explanations for data from four different experiments. Further, our model provides a rational explanation for why the influence of past experience on attentional control is short lived.

To investigate how top-down (TD) and bottom-up (BU) information is weighted in the guidance of human search behavior, we manipulated the proportions of BU and TD components in a saliency-based model. The model is biologically plausible and implements an artificial retina and a neuronal population code. The BU component is based on featurecontrast. TheTD component is defined by a feature-template match to a stored target representation. We compared the model's behavior at different mixturesof TD and BU components to the eye movement behavior of human observers performing the identical search task. We found that a purely TD model provides a much closer match to human behavior than any mixture model using BU information. Only when biological constraints areremoved (e.g., eliminating the retina) did a BU/TD mixture model begin to approximate human behavior.

We present a series of theoretical arguments supporting the claim that a large class of modern learning algorithms that rely solely on the smoothness prior-with similarity between examples expressed with a local kernel - are sensitive to the curse of dimensionality, or more precisely to the variability of the target. Our discussion covers supervised, semisupervised andunsupervised learning algorithms. These algorithms are found to be local in the sense that crucial properties of the learned function atx depend mostly on the neighbors of x in the training set. This makes them sensitive to the curse of dimensionality, well studied for classical nonparametric statistical learning. We show in the case of the Gaussian kernel that when the function to be learned has many variations, these algorithms require a number of training examples proportional to the number of variations, which could be large even though there may exist shortdescriptions of the target function, i.e. their Kolmogorov complexity maybe low. This suggests that there exist non-local learning algorithms that at least have the potential to learn about such structured but apparently complex functions (because locally they have many variations), whilenot using very specific prior domain knowledge.

Motivated by the problem of learning to detect and recognize objects with minimal supervision, we develop a hierarchical probabilistic model for the spatial structure of visual scenes. In contrast with most existing models, our approach explicitly captures uncertainty in the number of object instances depicted in a given image. Our scene model is based on the transformed Dirichlet process (TDP), a novel extension of the hierarchical DPin which a set of stochastically transformed mixture components are shared between multiple groups of data. For visual scenes, mixture components describe the spatial structure of visual features in an object-centered coordinate frame, while transformations model the object positionsin a particular image. Learning and inference in the TDP, which has many potential applications beyond computer vision, is based on an empirically effective Gibbs sampler. Applied to a dataset of partially labeledstreet scenes, we show that the TDP's inclusion of spatial structure improves detection performance, flexibly exploiting partially labeled training images.

Training a learning algorithm is a costly task. A major goal of active learning is to reduce this cost. In this paper we introduce a new algorithm, KQBC,which is capable of actively learning large scale problems by using selective sampling. The algorithm overcomes the costly sampling stepof the well known Query By Committee (QBC) algorithm by projecting onto a low dimensional space. KQBC also enables the use of kernels, providing a simple way of extending QBC to the nonlinear scenario. Sampling the low dimension space is done using the hit and run random walk. We demonstrate the success of this novel algorithm by applying it to both artificial and a real world problems.

Reinforcement learning models have long promised to unify computational, psychologicaland neural accounts of appetitively conditioned behavior. However,the bulk of data on animal conditioning comes from free-operant experiments measuring how fast animals will work for reinforcement. Existingreinforcement learning (RL) models are silent about these tasks, because they lack any notion of vigor. They thus fail to address thesimple observation that hungrier animals will work harder for food, as well as stranger facts such as their sometimes greater productivity evenwhen working for irrelevant outcomes such as water. Here, we develop an RL framework for free-operant behavior, suggesting that subjects choose how vigorously to perform selected actions by optimally balancing the costs and benefits of quick responding.

We present a generalization of temporal-difference networks to include temporally abstract options on the links of the question network.

We also find hyperparameters of the covariance function in the same joint optimization.

Sparse PCA seeks approximate sparse "eigenvectors" whose projections capture the maximal variance of data. As a cardinality-constrained and non-convex optimization problem, it is NPhard and is encountered in a wide range of applied fields, from bio-informatics to finance. Recent progress has focused mainly on continuous approximation and convex relaxation of the hard cardinality constraint. In contrast, we consider an alternative discrete spectral formulation based on variational eigenvalue bounds and provide an effective greedy strategy as well as provably optimal solutions using branch-and-bound search. Moreover, the exact methodology used reveals a simple renormalization step that improves approximate solutions obtained by any continuous method. The resulting performance gain of discrete algorithms is demonstrated on real-world benchmark data and in extensive Monte Carlo evaluation trials.

This paper presents a rigorous statistical analysis characterizing regimes in which active learning significantly outperforms classical passive learning. Activelearning algorithms are able to make queries or select sample locations in an online fashion, depending on the results of the previous queries. In some regimes, this extra flexibility leads to significantly faster rates of error decay than those possible in classical passive learning settings. Thenature of these regimes is explored by studying fundamental performance limits of active and passive learning in two illustrative nonparametric function classes. In addition to examining the theoretical potentialof active learning, this paper describes a practical algorithm capable of exploiting the extra flexibility of the active setting and provably improvingupon the classical passive techniques. Our active learning theory and methods show promise in a number of applications, including field estimation using wireless sensor networks and fault line detection.