Computer Go presents a challenging problem for machine learning agents. With the number of possible board states estimated to be larger than the number of hydrogen atoms in the universe, learning effective policies or board evaluation functions is extremely difficult. In this paper we describe Cortigo, a system that efficiently and autonomously learns useful generalizations for large state-space classification problems such as Go. Cortigo uses a hierarchical generative model loosely related to the human visual cortex to recognize Go board positions well enough to suggest promising next moves. We begin by briefly describing and providing motivation for research in the computer Go domain. We describe Cortigo’s ability to learn predictive models based on large subsets of the Go board and demonstrate how using Cortigo’s learned models as additive knowledge in a state-of-the-art computer Go player (Fuego) significantly improves its playing strength.

In order to better protect and conserve biodiversity, ecologists use machine learning and statistics to understand how species respond to their environment and to predict how they will respond to future climate change, habitat loss and other threats. A fundamental modeling task is to estimate the probability that a given species is present in (or uses) a site, conditional on environmental variables such as precipitation and temperature. For a limited number of species, survey data consisting of both presence and absence records are available, and can be used to fit a variety of conventional classification and regression models. For most species, however, the available data consist only of occurrence records --- locations where the species has been observed. In two closely-related but separate bodies of ecological literature, diverse special-purpose models have been developed that contrast occurrence data with a random sample of available environmental conditions. The most widespread statistical approaches involve either fitting an exponential model of species' conditional probability of presence, or fitting a naive logistic model in which the random sample of available conditions is treated as absence data; both approaches have well-known drawbacks, and do not necessarily produce valid probabilities. After summarizing existing methods, we overcome their drawbacks by introducing a new scaled binomial loss function for estimating an underlying logistic model of species presence/absence. Like the Expectation-Maximization approach of Ward et al. and the method of Steinberg and Cardell, our approach requires an estimate of population prevalence, $\Pr(y=1)$, since prevalence is not identifiable from occurrence data alone. In contrast to the latter two methods, our loss function is straightforward to integrate into a variety of existing modeling frameworks such as generalized linear and additive models and boosted regression trees. We also demonstrate that approaches by Lele and Keim and by Lancaster and Imbens that surmount the identifiability issue by making parametric data assumptions do not typically produce valid probability estimates.

A key problem in statistical modeling is model selection, how to choose a model at an appropriate level of complexity. This problem appears in many settings, most prominently in choosing the number ofclusters in mixture models or the number of factors in factor analysis. In this tutorial we describe Bayesian nonparametric methods, a class of methods that side-steps this issue by allowing the data to determine the complexity of the model. This tutorial is a high-level introduction to Bayesian nonparametric methods and contains several examples of their application.

We address the issue of knots selection for Gaussian predictive process methodology. Predictive process approximation provides an effective solution to the cubic order computational complexity of Gaussian process models. This approximation crucially depends on a set of points, called knots, at which the original process is retained, while the rest is approximated via a deterministic extrapolation. Knots should be few in number to keep the computational complexity low, but provide a good coverage of the process domain to limit approximation error. We present theoretical calculations to show that coverage must be judged by the canonical metric of the Gaussian process. This necessitates having in place a knots selection algorithm that automatically adapts to the changes in the canonical metric affected by changes in the parameter values controlling the Gaussian process covariance function. We present an algorithm toward this by employing an incomplete Cholesky factorization with pivoting and dynamic stopping. Although these concepts already exist in the literature, our contribution lies in unifying them into a fast algorithm and in using computable error bounds to finesse implementation of the predictive process approximation. The resulting adaptive predictive process offers a substantial automatization of Guassian process model fitting, especially for Bayesian applications where thousands of values of the covariance parameters are to be explored.

A nonparametric Bayesian extension of Factor Analysis (FA) is proposed where observed data $\mathbf{Y}$ is modeled as a linear superposition, $\mathbf{G}$, of a potentially infinite number of hidden factors, $\mathbf{X}$. The Indian Buffet Process (IBP) is used as a prior on $\mathbf{G}$ to incorporate sparsity and to allow the number of latent features to be inferred. The model's utility for modeling gene expression data is investigated using randomly generated data sets based on a known sparse connectivity matrix for E. Coli, and on three biological data sets of increasing complexity.

Many widely studied graphical models with latent variables lead to nontrivial constraints on the distribution of the observed variables. Inspired by the Bell inequalities in quantum mechanics, we refer to any linear inequality whose violation rules out some latent variable model as a "hidden variable test" for that model. Our main contribution is to introduce a sequence of relaxations which provides progressively tighter hidden variable tests. We demonstrate applicability to mixtures of sequences of i.i.d. variables, Bell inequalities, and homophily models in social networks. For the last, we demonstrate that our method provides a test that is able to rule out latent homophily as the sole explanation for correlations on a real social network that are known to be due to influence.

This paper presents new results for the (partial) maximum a posteriori (MAP) problem in Bayesian networks, which is the problem of querying the most probable state configuration of some of the network variables given evidence. It is demonstrated that the problem remains hard even in networks with very simple topology, such as binary polytrees and simple trees (including the Naive Bayes structure), which extends previous complexity results. Furthermore, a Fully Polynomial Time Approximation Scheme for MAP in networks with bounded treewidth and bounded number of states per variable is developed. Approximation schemes were thought to be impossible, but here it is shown otherwise under the assumptions just mentioned, which are adopted in most applications.

Learning to rank has received great attention in recent years as it plays a crucial role in information retrieval. The existing concept of learning to rank assumes that each training sample is associated with an instance and a reliable label. However, in practice, this assumption does not necessarily hold true. This study focuses on the learning to rank when each training instance is labeled by multiple annotators that may be unreliable. In such a scenario, no accurate labels can be obtained. This study proposes two learning approaches. One is to simply estimate the ground truth first and then to learn a ranking model with it. The second approach is a maximum likelihood learning approach which estimates the ground truth and learns the ranking model iteratively. The two approaches have been tested on both synthetic and real-world data. The results reveal that the maximum likelihood approach outperforms the first approach significantly and is comparable of achieving results with the learning model considering reliable labels. Further more, both the approaches have been applied for ranking the Web visual clutter.

Topic models have a wide range of applications, including modeling of text documents, images, user preferences, product rankings, and many others. However, learning optimal models may be difficult, especially for large problems. The reason is that inference techniques such as Gibbs sampling often converge to suboptimal models due to the abundance of local minima in large datasets. In this paper, we propose a general method of improving the performance of topic models. The method, called 'grouping transform', works by introducing auxiliary variables which represent assignments of the original model tokens to groups. Using these auxiliary variables, it becomes possible to resample an entire group of tokens at a time. This allows the sampler to make larger state space moves. As a result, better models are learned and performance is improved. The proposed ideas are illustrated on several topic models and several text and image datasets. We show that the grouping transform significantly improves performance over standard models.

Robots must perform tasks efficiently and reliably while acting underuncertainty. One way to achieve efficiency is to give the robot common-sense knowledge about the structure of the world. Reliable robot behaviour can be achieved by modelling the uncertaintyin the world probabilistically. We present a robot system that combines these two approaches and demonstrate the improvements in efficiency and reliability that result. Our first contribution is a probabilistic relational model integrating common-sense knowledge about the world in general, with observations of a particular environment. Our second contribution is a continual planning system which is able to plan in the large problems posed by that model, by automatically switching between decision-theoretic and classical procedures. We evaluate our system on object search tasks in two different real-world indoor environments. By reasoning about the trade-offs between possible courses of action with different informational effects, and exploiting the cues and general structures of those environments, our robot is able to consistently demonstrate efficient and reliable goal-directed behaviour.