Hashing, which tries to learn similarity-preserving binary codes for data representation, has been widely used for efficient nearest neighbor search in massive databases due to its fast query speed and low storage cost. Because it is NP hard to directly compute the best binary codes for a given data set, mainstream hashing methods typically adopt a two-stage strategy. In the first stage, several projected dimensions of real values are generated. Then in the second stage, the real values will be quantized into binary codes by thresholding. Currently, most existing methods use one single bit to quantize each projected dimension. One problem with this single-bit quantization (SBQ) is that the threshold typically lies in the region of the highest point density and consequently a lot of neighboring points close to the threshold will be hashed to totally different bits, which is unexpected according to the principle of hashing. In this paper, we propose a novel quantization strategy, called double-bit quantization (DBQ), to solve the problem of SBQ. The basic idea of DBQ is to quantize each projected dimension into double bits with adaptively learned thresholds. Extensive experiments on two real data sets show that our DBQ strategy can significantly outperform traditional SBQ strategy for hashing.

Significant progress has been made in the area of multiagent path finding/planning in the past decade (Silver 2005; van den Berg et al. 2009; Standley 2010; Luna and Bekris 2011; Wang and Botea 2011). In this work, we introduce a multi-agent path planning problem similar to that of (Standley (a) (b) (c) 2010) and aim at maximizing parallelism among the agents. That is, we seek a feasible plan that minimizes the Figure 1: a) A simple graph G. b) A gadget for splitting time it takes the last agent to reach its goal. To solve the an undirected edge through time steps.

Game Artificial Intelligence (Game AI) is a sub-discipline of Artificial Intelligence (AI) and Machine Learning (ML) that explores the ways in which AI and ML can augment player experiences in computer games. Storytelling is an integral part of many modern computer games; within games stories create context, motivate the player, and move the action forward. Interactive Narrative is the use of AI to create and manage stories within games, creating the perception that the player is a character in a dynamically unfolding and responsive story. This paper introduces Game AI and focuses on the open research problems of Interactive Narrative.

This paper describes the development and empirical testing of an intelligent tutoring system (ITS) with two emerging methodologies: (1) a partially observable Markov decision process (POMDP) for representing the learner model and (2) inquiry modeling, which informs the learner model with questions learners ask during instruction. POMDPs have been successfully applied to non-ITS domains but, until recently, have seemed intractable for large-scale intelligent tutoring challenges. New, ITS-specific representations leverage common regularities in intelligent tutoring to make a POMDP practical as a learner model. Inquiry modeling is a novel paradigm for informing learner models by observing rich features of learners’ help requests such as categorical content, context, and timing. The experiment described in this paper demonstrates that inquiry modeling and planning with POMDPs can yield significant and substantive learning improvements in a realistic, scenario-based training task.

In this paper we describe eBird, a citizen-science project that takes advantage of human observational capacity and machine learning methods to explore the synergies between human computation and mechanical computation. We call this model a Human/Computer Learning Network, whose core is an active learning feedback loop between humans and machines that dramatically improves the quality of both, and thereby continually improves the effectiveness of the network as a whole. Human/Computer Learning Networks leverage the contributions of a broad recruitment of human observers and processes their contributed data with Artificial Intelligence algorithms leading to a computational power that far exceeds the sum of the individual parts.

One of the key issues for transportation companies is to produce an optimal plan for the work of crew members. Crew planning consists of a sequence of phases, the first two corresponding to planning duties (sequences of trips to be done by crew members from their home base to their home base) and planning rosters (sequences of duties and rest days to be followed by crew members during a certain number of weeks). Both duty and roster planning are subject to a large number of constraints. Duty planning is constrained by intra-duty constraints and roster planning by inter-duty constraints. Since inter-duty constraints relate how duties can be combined into a roster, it is desirable that some of these constraints be transposed into the duty planning phase, as additional constraints, to guarantee that the duties produced in the first phase are "rosterable'' in the second phase. Both Artificial Intelligence (AI) and Operations Research (OR) have addressed duty planning, but for very large scale problems, OR has been far more successful due to its global vision of the problem. This paper discusses the use of AI local search to improve an OR-based duty planning optimizer that uses additional constraints.

In 2007 we presented a paper that described the application of Natural Language Processing (NLP) and Machine Translation (MT) for the automated translation of process build instructions from English to other languages to support Ford’s assembly plants in non-English speaking countries. This project has continued to evolve with the addition of new languages and improvements to the translation process. However, we discovered that there was a large demand for automated language translation across all of Ford Motor Company and we decided to expand the scope of our project to address these requirements. This paper will describe our efforts to meet all of Ford’s internal translation requirements with AI and MT technology and focus on the challenges and lessons that we learned from applying advanced technology across an entire corporation.

NASA and the international community are investing in the development of a commercial transportation infrastructure that includes the increased use of rotorcraft, specifically heli- copters and civil tilt rotors. However, there is significant con- cern over the impact of noise on the communities surrounding the transportation facilities. One way to address the rotorcraft noise problem is by exploiting powerful search techniques coming from artificial intelligence coupled with simulation and field tests to design low-noise flight profiles which can be tested in simulation or through field tests. This paper in- vestigates the use of simulation based on predictive physical models to facilitate the search for low-noise trajectories using local search combined with a robust noise simulator.

This article describes a new automatic transcription system in the Japanese Parliament which deploys our automatic speech recognition (ASR) technology. To achieve high recognition performance in spontaneous meeting speech, we have investigated an efficient training scheme with minimal supervision which can exploit a huge amount of real data. Specifically, we have proposed a lightly-supervised training scheme based on statistical language model transformation, which fills the gap between faithful transcripts of spoken utterances and final texts for documentation. Once this mapping is trained, we no longer need faithful transcripts for training both acoustic and language models. Instead, we can fully exploit the speech and text data available in Parliament as they are. This scheme also realizes a sustainable ASR system which evolves, i.e. update/re-train the models, only with speech and text generated during the system operation. The ASR system has been deployed in the Japanese Parliament since 2010, and consistently achieved character accuracy of nearly 90\%, which is useful for streamlining the transcription process.

Electronic health records (EHRs) are an emerging relational domain with large potential to improve clinical outcomes. We apply two statistical relational learning (SRL) algorithms to the task of predicting primary myocardial infarction. We show that one SRL algorithm, relational functional gradient boosting, outperforms propositional learners particularly in the medically-relevant high recall region. We observe that both SRL algorithms predict outcomes better than their propositional analogs and suggest how our methods can augment current epidemiological practices.