RoadNarrows has entered the “desktop-size” 5 degree of freedom robot arm, Hekateros, in the Small-Scale Manipulator Challenge, at the 2011 AAAI conference. Hekateros is utilizing a variety of sensors and software to successfully perceive and manipulate the chess gam

In this paper, we propose a bottom-up approach to generating short descriptive sentences from images, to enhance scene understanding. We demonstrate automatic methods for mapping the visual content in an image to natural spoken or written language. We also introduce a human-in-the-loop evaluation strategy that quantitatively captures the meaningfulness of the generated sentences. We recorded a correctness rate of 60.34% when human users were asked to judge the meaningfulness of the sentences generated from relatively challenging images. Also, our automatic methods compared well with the state-of-the-art techniques for the related computer vision tasks.

Query recommendation can not only effectively facilitate users to obtain their desired information but alsoincrease ads’ click-through rates. This paper presentsa general and highly efficient method for query recommendation. Given query sessions, we automatically generate many similar and dissimilar query-pairs as the prior knowledge. Then we learn a transformation from the prior knowledge to move similar queries closer such that similar queries tend to have similar hash values.This is formulated as minimizing the empirical error on the prior knowledge while maximizing the gap between the data and some partition hyperplanes randomly generated in advance. In the recommendation stage, we search queries that have similar hash values to the given query, rank the found queries and return the top K queries as the recommendation result. All the experimental results demonstrate that our method achieves encouraging results in terms of efficiency and recommendation performance.

K-flats is a model-based linear manifold clustering algorithm which has been successfully applied in many real-world scenarios. Though some previous works have shown that K-flats doesn’t always provide good performance, little effort has been devoted to analyze its inherent deficiency. In this paper, we address this challenge by showing that the deteriorative performance of K-flats can be attributed to the usual reconstruction error measure and the infinitely extending representations of linear models. Then we propose Localized K-flats algorithm (LKF), which introduces localized representations of linear models and a new distortion measure, to remove confusion among different clusters. Experiments on both synthetic and real-world data sets demonstrate the efficiency of the proposed algorithm. Moreover, preliminary experiments show that LKF has the potential to group manifolds with nonlinear structure.

Probabilistic Latent Semantic Analysis (PLSA) has been popularly used in document analysis. However, as it is currently formulated, PLSA strictly requires the number of word latent classes to be equal to the number of document latent classes. In this paper, we propose Bi-mixture PLSA, a new formulation of PLSA that allows the number of latent word classes to be different from the number of latent document classes. We further extend Bi-mixture PLSA to incorporate the sentence information, and propose Bi-mixture PLSA with sentence bases (Bi-PLSAS) to simultaneously cluster and summarize the documents utilizing the mutual influence of the document clustering and summarization procedures. Experiments on real-world datasets demonstrate the effectiveness of our proposed methods.

In this paper we present a data-driven approach to modeling end user energy consumption in residential and commercial buildings. Our model is based upon a data set of monthly electricity and gas bills, collected by a utility over the course of several years, for approximately 6,500 buildings in Cambridge, MA. In addition, we use publicly available tax assessor records and geographical survey information to determine corresponding features for the buildings. Using both parametric and non-parametric learning methods, we learn models that predict distributions over energy usage based upon these features, and use these models to develop two end-user systems. For utilities or authorized institutions (those who may obtain access to the full data) we provide a system that visualizes energy consumption for each building in the city; this allows companies to quickly identify outliers (buildings which use much more energy than expected even after conditioning on the relevant predictors), for instance allowing them to target homes for potential retrofits or tiered pricing schemes. For other end users, we provide an interface for entering their own electricity and gas usage, along with basic information about their home, to determine how their consumption compares to that of similar buildings as predicted by our model. Merely allowing users to contextualize their consumption in this way, relating it to the consumption in similar buildings, can itself produce behavior changes to significantly reduce consumption.

With the recent inclusion of inter-league games to professional sports leagues, a natural question is to determine the "best possible" inter-league schedule that retains all of the league's scheduling constraints to ensure competitive balance and fairness, while minimizing the total travel distance for both economic and environmental efficiency. To answer that question, this paper introduces the Bipartite Traveling Tournament Problem (BTTP) , the inter-league extension of the well-studied Traveling Tournament Problem. We prove that the 2n -team BTTP is NP-complete, but for small values of n , a distance-optimal inter-league schedule can be generated from an algorithm based on minimum-weight 4-cycle-covers. We apply our algorithm to the 12-team Nippon Professional Baseball (NPB) league in Japan, creating an inter-league tournament that reduces total team travel by 16% compared to the actual schedule played by these teams during the 2010 NPB season. We also analyze the problem of inter-league scheduling for the 30-team National Basketball Association (NBA), and develop a tournament schedule whose total inter-league travel distance is just 3.8% higher than the trivial theoretical lower bound.  

The success of transfer learning on a target task is highly dependent on the selected source data. Instance transfer methods reuse data from the source tasks to augment the training data for the target task. If poorly chosen, this source data may inhibit learning, resulting in negative transfer. The current most widely used algorithm for instance transfer, TrAdaBoost, performs poorly when given irrelevant source data. We present a novel task-based boosting technique for instance transfer that selectively chooses the source knowledge to transfer to the target task. Our approach performs boosting at both the instance level and the task level, assigning higher weight to those source tasks that show positive transferability to the target task, and adjusting the weights of individual instances within each source task via AdaBoost. We show that this combination of task- and instance-level boosting significantly improves transfer performance over existing instance transfer algorithms when given a mix of relevant and irrelevant source data, especially for small amounts of data on the target task.

Smart meters are intended to allow suppliers electricity network technologies, collectively called to access detailed energy consumption data and, more the smart grid (US Department Of Energy 2003; Galvin importantly, provide network information, such as real-time and Yeager 2008; UK Department of Energy and Climate pricing (RTP) signals, to consumers in an attempt to better Change 2009). A major component of this future vision is control or reduce demand when electricity is expensive that of energy storage. In particular, there is potential seen or carbon intensive on the grid (Hammerstrom et al. 2008; in the widespread adoption of small scale consumer storage Smith 2010). Accordingly, we envisage that micro-storage devices (i.e., micro-storage), which would allow consumers will be controlled by autonomous software agents that will to store electricity when demand is low, in order for react to RTP signals to minimise their owner's costs (i.e., it to be used during peak loads (Bathurst and Strbac 2003; they are self-interested). In this vein, we note our recent Ramchurn et al. 2011a; Vytelingum et al. 2010). This technology work (Vytelingum et al. 2010) in which we showed that, has the added advantage that it requires no significant when acting purely selfishly, large numbers of micro-storage change in how home appliances are used, and thus allows agents can cause instability in the aggregate demand profile.

We concern the problem of learning a Mahalanobis distance metric for improving nearest neighbor classification. Our work is built upon the large margin nearest neighbor (LMNN) classification framework. Due to the semidefiniteness constraint in the optimization problem of LMNN, it is not scalable in terms of the dimensionality of the input data. The original LMNN solver partially alleviates this problem by adopting alternating projection methods instead of standard interior-point methods. Still, at each iteration, the computation complexity is at least O(D 3 ) (D is the dimension of input data). In this work, we propose a column generation based algorithm to solve the LMNN optimization problem much more efficiently. Our algorithm is much more scalable in tha tat each iteration, it does not need full eigen-decomposition. Instead, we only need to find the leading eigen value and its corresponding eigen vector, which is of O(D 2 ) complexity. Experiments show the efficiency and efficacy of our algorithms.