Monte Carlo tree search (MCTS) is extremely popular in computer Go which determines each action by enormous simulations in a broad and deep search tree. However, human experts select most actions by pattern analysis and careful evaluation rather than brute search of millions of future interactions. In this paper, we propose a computer Go system that follows experts’ way of thinking and playing. Our system consists of two parts. The first part is a novel deep alternative neural network (DANN) used to generate candidates of next move. Compared with existing deep convolutional neural network (DCNN), DANN inserts recurrent layer after each convolutional layer and stacks them in an alternative manner. We show such setting can preserve more contexts of local features and its evolutions which are beneficial for move prediction. The second part is a long-term evaluation (LTE) module used to provide a reliable evaluation of candidates rather than a single probability from move predictor. This is consistent with human experts’ nature of playing since they can foresee tens of steps to give an accurate estimation of candidates. In our system, for each candidate, LTE calculates a cumulative reward after several future interactions when local variations are settled. Combining criteria from the two parts, our system determines the optimal choice of next move. For more comprehensive experiments, we introduce a new professional Go dataset (PGD), consisting of $253,233$ professional records. Experiments on GoGoD and PGD datasets show the DANN can substantially improve performance of move prediction over pure DCNN. When combining LTE, our system outperforms most relevant approaches and open engines based on MCTS.

Many idiomatic expressions can be interpreted literally or figuratively, depending on the context in which they occur. Developing an appropriate computational model of the context is crucial for automatic idiom usage recognition. While many existing methods incorporate some elements of context, they have not sufficiently captured the interactions between the linguistic properties of idiomatic expressions and the representations of the context. In this paper we perform an in-depth exploration of the role of representations of the context for idiom usage recognition; we highlight the advantages and limitations of different representation choices in existing methods in terms of known linguistic properties of idioms; we then propose a supervised ensemble method that selects representations adaptively for different idioms. Experimental result suggests that the proposed method performs better for a wider range of idioms than previous methods.

In this paper, we consider the problem of actively learning a linear classifier through query synthesis where the learner can construct artificial queries in order to estimate the true decision boundaries. This problem has recently gained a lot of interest in automated science and adversarial reverse engineering for which only heuristic algorithms are known. In such applications, queries can be constructed de novo to elicit information (e.g., automated science) or to evade detection with minimal cost (e.g., adversarial reverse engineering). We develop a general framework, called dimension coupling (DC), that 1) reduces a d-dimensional learning problem to d-1 low dimensional sub-problems, 2) solves each sub-problem efficiently, 3) appropriately aggregates the results and outputs a linear classifier, and 4) provides a theoretical guarantee for all possible schemes of aggregation. The proposed method is proved resilient to noise. We show that the DC framework avoids the curse of dimensionality: its computational complexity scales linearly with the dimension. Moreover, we show that the query complexity of DC is near optimal (within a constant factor of the optimum algorithm). To further support our theoretical analysis, we compare the performance of DC with the existing work. We observe that DC consistently outperforms the prior arts in terms of query complexity while often running orders of magnitude faster.

Belief Propagation (BP) is an iterative message-passing algorithm for performing inference in graphical models Convergent message-passing algorithms. There has (GMs), such as Markov Random Fields (MRFs). BP calculates been much research on finding variations to the update equations the marginal distribution for each unobserved node, of BP that guarantee convergence. These algorithms conditional on any observed nodes (Pearl 1988). It achieves are often similar in structure to the nonconvergent algorithms, this by propagating the information from a few observed yet it can be proven that the value of the variational nodes throughout the network by iteratively passing information problem (or its dual) improves at each iteration (Hazan and between neighboring nodes. It is known that when Shashua 2008; Heskes 2006; Meltzer, Globerson, and Weiss the graphical model has a tree structure, then BP converges 2009). Another body of recent papers have suggested to to the true marginals (according to exact probabilistic inference) solve the convergence problems of MMinference by linearizing after a finite number of iterations.

The formalism of multi-objective influence diagrams has recently been developed for modeling and solving sequential decision problems under uncertainty and multiple objectives. Since utility values representing the decision maker's preferences are only partially ordered (e.g., by the Pareto order) we no longer have a unique maximal value of expected utility, but a set of them. Computing the set of maximal values of expected utility and the corresponding policies can be computationally very challenging. In this paper, we consider alternative notions of optimality, one of the most important one being the notion of possibly optimal, namely optimal in at least one scenario compatible with the inter-objective tradeoffs. We develop a variable elimination algorithm for computing the set of possibly optimal expected utility values, prove formally its correctness, and compare variants of the algorithm experimentally.

We present new algorithms for learning Bayesian networks from data with missing values using a data augmentation approach. An exact Bayesian network learning algorithm is obtained by recasting the problem into a standard Bayesian network learning problem without missing data. As expected, the exact algorithm does not scale to large domains. We build on the exact method to create an approximate algorithm using a hill-climbing technique. This algorithm scales to large domains so long as a suitable standard structure learning method for complete data is available. We perform a wide range of experiments to demonstrate the benefits of learning Bayesian networks with such new approach.

We propose a model-based approach to hierarchical reinforcement learning that exploits shared knowledge and selective execution at different levels of abstraction, to efficiently solve large, complex problems. Our framework adopts a new transition dynamics learning algorithm that identifies the common action-feature combinations of the subtasks, and evaluates the subtask execution choices through simulation. The framework is sample efficient, and tolerates uncertain and incomplete problem characterization of the subtasks. We test the framework on common benchmark problems and complex simulated robotic environments. It compares favorably against the state-of-the-art algorithms, and scales well in very large problems.

An intriguing application of transfer learning emerges when tasks arise with similar, but not identical, dynamics. Hidden Parameter Markov Decision Processes (HiP-MDP) embed these tasks into a low-dimensional space; given the embedding parameters one can identify the MDP for a particular task. However, the original formulation of HiP-MDP had a critical flaw: the embedding uncertainty was modeled independently of the agent's state uncertainty, requiring an arduous training procedure. In this work, we apply a Gaussian Process latent variable model to jointly model the dynamics and the embedding, leading to a more elegant formulation, one that allows for better uncertainty quantification and thus more robust transfer.

Nonparametric inference techniques provide promising tools for probabilistic reasoning in high-dimensional nonlinear systems.Most of these techniques embed distributions into reproducing kernel Hilbert spaces (RKHS) and rely on the kernel Bayes' rule (KBR) to manipulate the embeddings. However, the computational demands of the KBR scale poorly with the number of samples and the KBR often suffers from numerical instabilities. In this paper, we present the kernel Kalman rule (KKR) as an alternative to the KBR.The derivation of the KKR is based on recursive least squares, inspired by the derivation of the Kalman innovation update.We apply the KKR to filtering tasks where we use RKHS embeddings to represent the belief state, resulting in the kernel Kalman filter (KKF).We show on a nonlinear state estimation task with high dimensional observations that our approach provides a significantly improved estimation accuracy while the computational demands are significantly decreased.

Linear Discriminant Analysis (LDA) is a well-known method for dimension reduction and classification with focus on discriminative feature selection. However, how to discover discriminative as well as representative features in LDA model has not been explored. In this paper, we propose a latent Fisher discriminant model with representative feature discovery in an semi-supervised manner. Specifically, our model leverages advantages of both discriminative and generative models by generalizing LDA with data-driven prior over the latent variables. Thus, our method combines multi-class, latent variables and dimension reduction in an unified Bayesian framework. We test our method on MUSK and Corel datasets and yield competitive results compared to baselines. We also demonstrate its capacity on the challenging TRECVID MED11 dataset for semantic keyframe extraction and conduct a human-factors ranking-based experimental evaluation, which clearly demonstrates our proposed method consistently extracts more semantically meaningful keyframes than challenging baselines.