In massive open online courses (MOOCs), peer grading serves as a critical tool for scaling the grading of complex, open-ended assignments to courses with tens or hundreds of thousands of students. But despite promising initial trials, it does not always deliver accurate results compared to human experts. In this paper, we develop algorithms for estimating and correcting for grader biases and reliabilities, showing significant improvement in peer grading accuracy on real data with 63,199 peer grades from Coursera's HCI course offerings --- the largest peer grading networks analysed to date. We relate grader biases and reliabilities to other student factors such as student engagement, performance as well as commenting style. We also show that our model can lead to more intelligent assignment of graders to gradees.

Bayesian network structure learning algorithms with limited data are being used in domains such as systems biology and neuroscience to gain insight into the underlying processes that produce observed data. Learning reliable networks from limited data is difficult, therefore transfer learning can improve the robustness of learned networks by leveraging data from related tasks. Existing transfer learning algorithms for Bayesian network structure learning give a single maximum a posteriori estimate of network models. Yet, many other models may be equally likely, and so a more informative result is provided by Bayesian structure discovery. Bayesian structure discovery algorithms estimate posterior probabilities of structural features, such as edges. We present transfer learning for Bayesian structure discovery which allows us to explore the shared and unique structural features among related tasks. Efficient computation requires that our transfer learning objective factors into local calculations, which we prove is given by a broad class of transfer biases. Theoretically, we show the efficiency of our approach. Empirically, we show that compared to single task learning, transfer learning is better able to positively identify true edges. We apply the method to whole-brain neuroimaging data.

We present a dynamic algorithm for solving the Longest Common Subsequence Problem using Ant Colony Optimization Technique. The Ant Colony Optimization Technique has been applied to solve many problems in Optimization Theory, Machine Learning and Telecommunication Networks etc. In particular, application of this theory in NP-Hard Problems has a remarkable significance. Given two strings, the traditional technique for finding Longest Common Subsequence is based on Dynamic Programming which consists of creating a recurrence relation and filling a table of size . The proposed algorithm draws analogy with behavior of ant colonies function and this new computational paradigm is known as Ant System. It is a viable new approach to Stochastic Combinatorial Optimization. The main characteristics of this model are positive feedback, distributed computation, and the use of constructive greedy heuristic. Positive feedback accounts for rapid discovery of good solutions, distributed computation avoids premature convergence and greedy heuristic helps find acceptable solutions in minimum number of stages. We apply the proposed methodology to Longest Common Subsequence Problem and give the simulation results. The effectiveness of this approach is demonstrated by efficient Computational Complexity. To the best of our knowledge, this is the first Ant Colony Optimization Algorithm for Longest Common Subsequence Problem.

ETP is NP Hard combinatorial optimization problem. It has received tremendous research attention during the past few years given its wide use in universities. In this Paper, we develop three mathematical models for NSOU, Kolkata, India using FILP technique. To deal with impreciseness and vagueness we model various allocation variables through fuzzy numbers. The solution to the problem is obtained using Fuzzy number ranking method. Each feasible solution has fuzzy number obtained by Fuzzy objective function. The different FILP technique performance are demonstrated by experimental data generated through extensive simulation from NSOU, Kolkata, India in terms of its execution times. The proposed FILP models are compared with commonly used heuristic viz. ILP approach on experimental data which gives an idea about quality of heuristic. The techniques are also compared with different Artificial Intelligence based heuristics for ETP with respect to best and mean cost as well as execution time measures on Carter benchmark datasets to illustrate its effectiveness. FILP takes an appreciable amount of time to generate satisfactory solution in comparison to other heuristics. The formulation thus serves as good benchmark for other heuristics. The experimental study presented here focuses on producing a methodology that generalizes well over spectrum of techniques that generates significant results for one or more datasets. The performance of FILP model is finally compared to the best results cited in literature for Carter benchmarks to assess its potential. The problem can be further reduced by formulating with lesser number of allocation variables it without affecting optimality of solution obtained. FLIP model for ETP can also be adapted to solve other ETP as well as combinatorial optimization problems.

In India financial markets have existed for many years. A functionally accented, diverse, efficient and flexible financial system is vital to the national objective of creating a market driven, productive and competitive economy. Today markets of varying maturity exist in equity, debt, commodities and foreign exchange. In this work we attempt to generate prediction rules scheme for stock price movement at Bombay Stock Exchange using an important Soft Computing paradigm viz., Rough Fuzzy Multi Layer Perception. The use of Computational Intelligence Systems such as Neural Networks, Fuzzy Sets, Genetic Algorithms, etc. for Stock Market Predictions has been widely established. The process is to extract knowledge in the form of rules from daily stock movements. These rules can then be used to guide investors. To increase the efficiency of the prediction process, Rough Sets is used to discretize the data. The methodology uses a Genetic Algorithm to obtain a structured network suitable for both classification and rule extraction. The modular concept, based on divide and conquer strategy, provides accelerated training and a compact network suitable for generating a minimum number of rules with high certainty values. The concept of variable mutation operator is introduced for preserving the localized structure of the constituting Knowledge Based sub-networks, while they are integrated and evolved. Rough Set Dependency Rules are generated directly from the real valued attribute table containing Fuzzy membership values. The paradigm is thus used to develop a rule extraction algorithm. The extracted rules are compared with some of the related rule extraction techniques on the basis of some quantitative performance indices. The proposed methodology extracts rules which are less in number, are accurate, have high certainty factor and have low confusion with less computation time.

Games have played a prominent role as a test-bed for advancements in the field of Artificial Intelligence ever since its foundation over half a century ago, resulting in highly specialized world-class game-playing systems being developed for various games. The establishment of the International General Game Playing Competition in 2005, however, resulted in a renewed interest in more general problem solving approaches to game playing. In general game playing (GGP) the goal is to create game-playing systems that autonomously learn how to skillfully play a wide variety of games, given only the descriptions of the game rules. In this paper we review the history of the competition, discuss progress made so far, and list outstanding research challenges.

Now entering its eighth year, the Annual Computer Poker Competition (ACPC) is the premier event within the field of computer poker. With both academic and nonacademic competitors from around the world, the competition provides an open and international venue for benchmarking computer poker agents. We describe the competition's origins and evolution, current events, and winning techniques.

This special issue of the AI Magazine is devoted to some exemplar works of AI on mobile devices. It includes four works that range from mobile activity recognition and air quality detection to machine translation and image compression.

Coming with the ever growing computational power of mobile devices, mobile visual search have undergone an evolution in techniques and applications. A significant trend is low bit rate visual search, where compact visual descriptors are extracted directly over a mobile and delivered as queries rather than raw images to reduce the query transmission latency. In this article, we introduce our work on low bit rate mobile landmark search, in which a compact yet discriminative landmark image descriptor is extracted by using location context such as GPS, crowd-sourced hotspot WLAN, and cell tower locations. The compactness originates from the bag-of-words image representation, with an offline learning from geotagged photos from online photo sharing websites including Flickr and Panoramio. The learning process involves segmenting the landmark photo collection by discrete geographical regions using Gaussian mixture model, and then boosting a ranking sensitive vocabulary within each region, with an “entropy” based descriptor compactness feedback to refine both phases iteratively. In online search, when entering a geographical region, the codebook in a mobile device are downstream adapted to generate extremely compact descriptors with promising discriminative ability. We have deployed landmark search apps to both HTC and iPhone mobile phones, working over the database of million scale images in typical areas like Beijing, New York, and Barcelona, and others. Our descriptor outperforms alternative compact descriptors (Chen et al. 2009; Chen et al., 2010; Chandrasekhar et al. 2009a; Chandrasekhar et al. 2009b) with significant margins. Beyond landmark search, this article will summarize the MPEG standarization progress of compact descriptor for visual search (CDVS) (Yuri et al. 2010; Yuri et al. 2011) towards application interoperability.

We consider multi-agent planning in which the agents' optimal plans are solutions to mixed-integer programs (MIP) that are coupled via integer constraints. While in principle, one could find the joint solution by combining the separate problems into one large joint centralized MIP, this approach rapidly becomes intractable for growing numbers of agents and large problem domains. To address this issue, we propose an iterative approach that combines conflict detection with constraint-generation whereby the agents plan repeatedly until all conflicts are resolved. In each planning iteration, the agents plan with as few other agents and interaction-constraints as possible. This yields an optimal method that can reduce computation markedly. We test our approach in the context of multi-agent collision avoidance in graphs with indivisible flows. Our initial simulations on randomized graph routing problems confirm predicted optimality and reduced computational effort.