In density estimation task, maximum entropy model (Maxent) can effectively use reliable prior information via certain constraints, i.e., linear constraints without empirical parameters. However, reliable prior information is often insufficient, and the selection of uncertain constraints becomes necessary but poses considerable implementation complexity. Improper setting of uncertain constraints can result in overfitting or underfitting. To solve this problem, a generalization of Maxent, under Tsallis entropy framework, is proposed. The proposed method introduces a convex quadratic constraint for the correction of (expected) Tsallis entropy bias (TEB). Specifically, we demonstrate that the expected Tsallis entropy of sampling distributions is smaller than the Tsallis entropy of the underlying real distribution. This expected entropy reduction is exactly the (expected) TEB, which can be expressed by a closed-form formula and act as a consistent and unbiased correction. TEB indicates that the entropy of a specific sampling distribution should be increased accordingly. This entails a quantitative re-interpretation of the Maxent principle. By compensating TEB and meanwhile forcing the resulting distribution to be close to the sampling distribution, our generalized TEBC Maxent can be expected to alleviate the overfitting and underfitting. We also present a connection between TEB and Lidstone estimator. As a result, TEB-Lidstone estimator is developed by analytically identifying the rate of probability correction in Lidstone. Extensive empirical evaluation shows promising performance of both TEBC Maxent and TEB-Lidstone in comparison with various state-of-the-art density estimation methods.

Sampling-based motion planners are an effective means for generating collision-free motion paths. However, the quality of these motion paths (with respect to quality measures such as path length, clearance, smoothness or energy) is often notoriously low, especially in high-dimensional configuration spaces. We introduce a simple algorithm for merging an arbitrary number of input motion paths into a hybrid output path of superior quality, for a broad and general formulation of path quality. Our approach is based on the observation that the quality of certain sub-paths within each solution may be higher than the quality of the entire path. A dynamic-programming algorithm, which we recently developed for comparing and clustering multiple motion paths, reduces the running time of the merging algorithm significantly. We tested our algorithm in motion-planning problems with up to 12 degrees of freedom. We show that our algorithm is able to merge a handful of input paths produced by several different motion planners to produce output paths of much higher quality.

Recent studies in the field of human vision science suggest that the human responses to the stimuli on a visual display are non-deterministic. People may attend to different locations on the same visual input at the same time. Based on this knowledge, we propose a new stochastic model of visual attention by introducing a dynamic Bayesian network to predict the likelihood of where humans typically focus on a video scene. The proposed model is composed of a dynamic Bayesian network with 4 layers. Our model provides a framework that simulates and combines the visual saliency response and the cognitive state of a person to estimate the most probable attended regions. Sample-based inference with Markov chain Monte-Carlo based particle filter and stream processing with multi-core processors enable us to estimate human visual attention in near real time. Experimental results have demonstrated that our model performs significantly better in predicting human visual attention compared to the previous deterministic models.

We develop multiattribute auctions that accommodate generalized additive independent (GAI) preferences. We propose an iterative auction mechanism that maintains prices on potentially overlapping GAI clusters of attributes, thus decreases elicitation and computational burden, and creates an open competition among suppliers over a multidimensional domain. Most significantly, the auction is guaranteed to achieve surplus which approximates optimal welfare up to a small additive factor, under reasonable equilibrium strategies of traders. The main departure of GAI auctions from previous literature is to accommodate non-additive trader preferences, hence allowing traders to condition their evaluation of specific attributes on the value of other attributes. At the same time, the GAI structure supports a compact representation of prices, enabling a tractable auction process. We perform a simulation study, demonstrating and quantifying the significant efficiency advantage of more expressive preference modeling. We draw random GAI-structured utility functions with various internal structures, generate additive functions that approximate the GAI utility, and compare the performance of the auctions using the two representations. We find that allowing traders to express existing dependencies among attributes improves the economic efficiency of multiattribute auctions.

We present DCL-PC: a logic for reasoning about how the abilities of agents and coalitions of agents are altered by transferring control from one agent to another. The logical foundation of DCL-PC is CL-PC, a logic for reasoning about cooperation in which the abilities of agents and coalitions of agents stem from a distribution of atomic Boolean variables to individual agents -- the choices available to a coalition correspond to assignments to the variables the coalition controls. The basic modal constructs of DCL-PC are of the form `coalition C can cooperate to bring about phi'. DCL-PC extends CL-PC with dynamic logic modalities in which atomic programs are of the form `agent i gives control of variable p to agent j'; as usual in dynamic logic, these atomic programs may be combined using sequence, iteration, choice, and test operators to form complex programs. By combining such dynamic transfer programs with cooperation modalities, it becomes possible to reason about how the power of agents and coalitions is affected by the transfer of control. We give two alternative semantics for the logic: a `direct' semantics, in which we capture the distributions of Boolean variables to agents; and a more conventional Kripke semantics. We prove that these semantics are equivalent, and then present an axiomatization for the logic. We investigate the computational complexity of model checking and satisfiability for DCL-PC, and show that both problems are PSPACE-complete (and hence no worse than the underlying logic CL-PC). Finally, we investigate the characterisation of control in DCL-PC. We distinguish between first-order control -- the ability of an agent or coalition to control some state of affairs through the assignment of values to the variables under the control of the agent or coalition -- and second-order control -- the ability of an agent to exert control over the control that other agents have by transferring variables to other agents. We give a logical characterisation of second-order control.

We present a novel framework for learning to interpret and generate language using only perceptual context as supervision. We demonstrate its capabilities by developing a system that learns to sportscast simulated robot soccer games in both English and Korean without any language-specific prior knowledge. Training employs only ambiguous supervision consisting of a stream of descriptive textual comments and a sequence of events extracted from the simulation trace. The system simultaneously establishes correspondences between individual comments and the events that they describe while building a translation model that supports both parsing and generation. We also present a novel algorithm for learning which events are worth describing. Human evaluations of the generated commentaries indicate they are of reasonable quality and in some cases even on par with those produced by humans for our limited domain.

Decentralized planning in uncertain environments is a complex task generally dealt with by using a decision-theoretic approach, mainly through the framework of Decentralized Partially Observable Markov Decision Processes (DEC-POMDPs). Although DEC-POMDPS are a general and powerful modeling tool, solving them is a task with an overwhelming complexity that can be doubly exponential. In this paper, we study an alternate formulation of DEC-POMDPs relying on a sequence-form representation of policies. From this formulation, we show how to derive Mixed Integer Linear Programming (MILP) problems that, once solved, give exact optimal solutions to the DEC-POMDPs. We show that these MILPs can be derived either by using some combinatorial characteristics of the optimal solutions of the DEC-POMDPs or by using concepts borrowed from game theory. Through an experimental validation on classical test problems from the DEC-POMDP literature, we compare our approach to existing algorithms. Results show that mathematical programming outperforms dynamic programming but is less efficient than forward search, except for some particular problems. The main contributions of this work are the use of mathematical programming for DEC-POMDPs and a better understanding of DEC-POMDPs and of their solutions. Besides, we argue that our alternate representation of DEC-POMDPs could be helpful for designing novel algorithms looking for approximate solutions to DEC-POMDPs.

Semantic technologies are available, and gain popularity on the Web as well as on the desktop, but both (desktop and Web) act as large data silos, making personal and online data difficult to interlink. We propose a system that enables easy publishing of personal notes as linked social media content, while at the same time semantically enriching the desktop resources with information retrieved from the Linked Data cloud. The transformation, publication and linking process is integrated with the familiar desktop applications and online blogging platforms, providing a better usability experience.

Development is fundamentally about understanding people, their motivations, behaviors and reactions. We have two primary means of understanding people — observing what they do, and what they say. As the AI4D community has noted, people's increased use of mobile devices has led to a wealth of new data relevant to these topics. We are on the cusp of developing incredibly powerful tools that can help us understand how human beings migrate, transact and acquire wealth. This could have a large impact on how we determine policies and allocate resources. Most of this analysis has tended to focus on what people do — where they go, who they talk to, what they buy, etc. I argue that what people say is an equally rich source of development data, often containing information that cannot be obtained from people's actions, such as their needs, hopes and aspirations. Voice is the most natural form of communication, especially for people who speak a non-mainstream language, and/or have marginal literacy skills.  These are often exactly those populations who are most disenfranchised, and therefore most need their voices to be heard.

Diabetic retinopathy, an eye disorder caused by diabetes, is the primary cause of blindness in America and over 99% of cases in India. India and China currently account for over 90 million diabetic patients and are on the verge of an explosion of diabetic populations. This may result in an unprecedented number of persons becoming blind unless diabetic retinopathy can be detected early. Aravind Eye Hospitals is the largest eye care facility in the world, handling over 2 million patients per year. The hospital is on a massive drive throughout southern India to detect diabetic retinopathy at an early stage. To that end, a group of 10-15 physicians are responsible for manually diagnosing over 2 million retinal images per year to detect diabetic retinopathy. While the task is extremely laborious, a large fraction of cases turn out to be normal indicating that much of this time is spent diagnosing completely normal cases. This paper describes our early experiences working with Aravind Eye Hospitals to develop an automated system to detect diabetic retinopathy from retinal images. The automated diabetic retinopathy problem is a hard computer vision problem whose goal is to detect features of retinopathy, such as hemorrhages and exudates, in retinal color fundus images. We describe our initial efforts towards building such a system using a range of computer vision techniques and discuss the potential impact on early detection of diabetic retinopathy.