Special tracks are a vital part of the FLAIRS Thanks go to the authors of both accepted and rejected conferences, with 11 held at FLAIRS-25. Over 90 papers; the special track coordinator Chutima percent of the papers were reviewed by four or Boonthum-Denecke and all the special track organizers; more reviewers, and all papers were reviewed by at the program committees and their reviewers; least three. These were coordinated by the program the invited speakers; Chad Lane for organizing committees of the general conference and the special the conference; Jean Gerber for administering the tracks. The accepted submissions include 74 conference; the Florida Artificial International Research full papers (19 from the general conference and 55 Society for maintaining the conference series; from the special tracks), 27 short papers presented the Association for the Advancement of Artificial as posters (6 from the general conference and 21 Intelligence for its cooperation with the conference; from the special tracks), and 20 poster abstracts Mike Hamilton for organizing the publication that appear in these proceedings. of the proceedings; and EasyChair for hosting the review process. The program included five invited talks: Bill Swartout, the Director of Technology and Research Professor at the University of Southern California's

Our motivation believe our results will be of special interest to researchers for this work comes from the fact that with the large from the field of medical image analysis, as these images amounts of data that the SDO mission started transmitting, seem to be the closest to our dataset [21. We also identify hand labeling (commonly used by solar physicist in the last some interesting combinations of dimensionality reduction decades) of these images is simply impossible. There have methods and classifiers that behave differently across the been several successful CBIR systems for medical images presented datasets. Our research problem in Solar physics is [2] as well as in other domains [3]; none of them, however, of great practical relevance for Earth's climate since solar have dealt with the volume of data that the SDO mission flares endanger the lives of passengers on commercial airline generates. This NASA mission, only with its Atmospheric routes going over the poles, interrupt radio communications Imaging Assembly (AIA), generates eight 4096 pixels x in bands the military uses, can (and have) knocked 4096 pixels images every 10 seconds. This leads to a data down power grids. The systematic feature recognition and transmission rate of approximately 700 gigabytes per day the study of the metadata, is a key component of the ultimate only from the AIA component (the entire mission is expected prediction of solar activity (space weather).

The area of argumentation theory is an increasingly important area of artificial intelligence and mechanisms that are able to automatically detect the argument structure provide a novel area of research. This paper considers the use of kernel methods for argumentation detection and classification. It shows that a classification accuracy of 65%, can be attained using Natural Language Processing based kernel approaches, which do not require any heuristic choice of features.

One of the consequences of the growth in AI research in South Africa in recent years is the establishment of a number of research hubs involved in AI activities ranging from mobile robotics and computational intelligence, to knowledge representation and reasoning, and human language technologies. In this survey we take the reader through a quick tour of the research being conducted at these hubs, and touch on an initiative to maintain and extend the current level of interest in AI research in the country.

Modern SAT solvers are routinely used as core solving engines in vast numbers of different AI and industrial applications. In this short article, we will provide an overview of the SAT solver competitions. The solvers), and another one based on wall clock time, second SAT competition took place during the second which promotes solvers using all available Dimacs challenge in 1993 (Johnson and Trick resources to answer as quickly as possible (for 1996). Another SAT competition took place in answers incorrectly if it reports satisfiable but Beijing in 1996, organized by James Crawford. Each survey propagation (Braunstein and Zecchina category is defined through the type of instances 2004), a new approach to efficiently solve randomly used as benchmarks.

In this article we review the 2011 International Planning Competition. We give an overview of the history of the competition, discussing how it has developed since its first edition in 1998. The 2011 competition was run in three main separate tracks: the deterministic (classical) track; the learning track; and the uncertainty track. Each track proposed its own distinct set of new challenges and the participants rose to these admirably, the results of each track showing promising progress in each area. The competition attracted a record number of participants this year, showing its continued and strong position as a major central pillar of the international planning research community.

According to a 2008 OECD review of national policies for education in South Africa, typically only 15 percent to 18 percent of secondary school students who sit for their final year exams every year qualify automatically for university-level education; and this number seems to be decreasing as more students choose to complete subjects on so-called standard grade instead of higher grade, a trend that is especially apparent for mathematics and science, the two fields with critical skills shortages in the country. The South African tertiary education sector is quite small for a country with a population of around 50 million, with 11 "traditional" universities, 6 technical universities, and 6 comprehensive universities. The latter university types focus on more technical or vocational education. The public sector also funds 16 research institutions. In spite of these obstacles, South African universities participate in world-class research activities in many fields and range among the best on the African continent.

Imaging spectrometers measure electromagnetic energy scattered in their instantaneous field view in hundreds or thousands of spectral channels with higher spectral resolution than multispectral cameras. Imaging spectrometers are therefore often referred to as hyperspectral cameras (HSCs). Higher spectral resolution enables material identification via spectroscopic analysis, which facilitates countless applications that require identifying materials in scenarios unsuitable for classical spectroscopic analysis. Due to low spatial resolution of HSCs, microscopic material mixing, and multiple scattering, spectra measured by HSCs are mixtures of spectra of materials in a scene. Thus, accurate estimation requires unmixing. Pixels are assumed to be mixtures of a few materials, called endmembers. Unmixing involves estimating all or some of: the number of endmembers, their spectral signatures, and their abundances at each pixel. Unmixing is a challenging, ill-posed inverse problem because of model inaccuracies, observation noise, environmental conditions, endmember variability, and data set size. Researchers have devised and investigated many models searching for robust, stable, tractable, and accurate unmixing algorithms. This paper presents an overview of unmixing methods from the time of Keshava and Mustard's unmixing tutorial [1] to the present. Mixing models are first discussed. Signal-subspace, geometrical, statistical, sparsity-based, and spatial-contextual unmixing algorithms are described. Mathematical problems and potential solutions are described. Algorithm characteristics are illustrated experimentally.

Kernel methods are among the most popular techniques in machine learning. From a frequentist/discriminative perspective they play a central role in regularization theory as they provide a natural choice for the hypotheses space and the regularization functional through the notion of reproducing kernel Hilbert spaces. From a Bayesian/generative perspective they are the key in the context of Gaussian processes, where the kernel function is also known as the covariance function. Traditionally, kernel methods have been used in supervised learning problem with scalar outputs and indeed there has been a considerable amount of work devoted to designing and learning kernels. More recently there has been an increasing interest in methods that deal with multiple outputs, motivated partly by frameworks like multitask learning. In this paper, we review different methods to design or learn valid kernel functions for multiple outputs, paying particular attention to the connection between probabilistic and functional methods.

In a deterministic world, a planning agent can be certain of the consequences of its planned sequence of actions. Not so, however, in dynamic, stochastic domains where Markov decision processes are commonly used. Unfortunately these suffer from the `curse of dimensionality': if the state space is a Cartesian product of many small sets (`dimensions'), planning is exponential in the number of those dimensions. Our new technique exploits the intuitive strategy of selectively ignoring various dimensions in different parts of the state space. The resulting non-uniformity has strong implications, since the approximation is no longer Markovian, requiring the use of a modified planner. We also use a spatial and temporal proximity measure, which responds to continued planning as well as movement of the agent through the state space, to dynamically adapt the abstraction as planning progresses. We present qualitative and quantitative results across a range of experimental domains showing that an agent exploiting this novel approximation method successfully finds solutions to the planning problem using much less than the full state space. We assess and analyse the features of domains which our method can exploit.