We describe ongoing research towards building a cognitively plausible system for near one-shot learning of the meanings of attribute words and object names, by grounding them in a sensory model. The system learns incrementally from human demonstrations recorded with the Microsoft Kinect, in which the demonstrator can use unrestricted natural language descriptions. We achieve near-one shot learning of simple objects and attributes by focusing solely on examples where the learning agent is confident, ignoring the rest of the data. We evaluate the system's learning ability by having it generate descriptions of presented objects, including objects it has never seen before, and comparing the system response against collected human descriptions of the same objects. We propose that our method of retrieving object examples with a k-nearest neighbor classifier using Mahalanobis distance corresponds to a cognitively plausible representation of objects. Our initial results show promise for achieving rapid, near one-shot, incremental learning of word meanings.

Many high-dimensional data sets that lie on a low-dimensional manifold exhibit nontrivial regularities at multiple scales. Most work in manifold learning ignores this multiscale structure. In this paper, we propose approaches to explore the deep structure of manifolds. The proposed approaches are based on the diffusion wavelets framework, data driven, and able to directly process directional neighborhood relationships without ad-hoc symmetrization. The proposed multiscale algorithms are evaluated using both synthetic and real-world data sets, and shown to outperform previous manifold learning methods.

In a lifelong learning framework, an agent acquires knowledge incrementally over consecutive learning tasks, continually building upon its experience. Recent lifelong learning algorithms have achieved nearly identical performance to batch multi-task learning methods while reducing learning time by three orders of magnitude. In this paper, we further improve the scalability of lifelong learning by developing curriculum selection methods that enable an agent to actively select the next task to learn in order to maximize performance on future learning tasks. We demonstrate that active task selection is highly reliable and effective, allowing an agent to learn high performance models using up to 50% fewer tasks than when the agent has no control over the task order. We also explore a variant of transfer learning in the lifelong learning setting in which the agent can focus knowledge acquisition toward a particular target task.

The role of kernels is central to machine learning. Motivated by the importance of power-law distributions in statistical modeling, in this paper, we propose the notion of power-law kernels to investigate power-laws in learning problem. We propose two power-law kernels by generalizing Gaussian and Laplacian kernels. This generalization is based on distributions, arising out of maximization of a generalized information measure known as nonextensive entropy that is very well studied in statistical mechanics. We prove that the proposed kernels are positive definite, and provide some insights regarding the corresponding Reproducing Kernel Hilbert Space (RKHS). We also study practical significance of both kernels in classification and regression, and present some simulation results.

Recently, a Euclidean heuristic (EH) has been proposed for A* search. EH exploits manifold learning methods to construct an embedding of the state space graph, and derives an admissible heuristic distance between two states from the Euclidean distance between their respective embedded points. EH has shown good performance and memory efficiency in comparison to other existing heuristics such as differential heuristics. However, its potential has not been fully explored. In this paper, we propose a number of techniques that can significantly improve the quality of EH. We propose a goal-oriented manifold learning scheme that optimizes the Euclidean distance to goals in the embedding while maintaining admissibility and consistency. We also propose a state heuristic enhancement technique to reduce the gap between heuristic and true distances. The enhanced heuristic is admissible but no longer consistent. We then employ a modified search algorithm, known as B' algorithm, that achieves optimality with inconsistent heuristics using consistency check and propagation. We demonstrate the effectiveness of the above techniques and report un-matched reduction in search costs across several non-trivial benchmark search problems.

This paper presents the results of developing subjectivity classifiers for Implicit Opinion Question (IOQ) identification. IOQs are defined as opinion questions with no opinion words. An IOQ example is "will the U.S. government pay more attention to the Pacific Rim?" Our analysis on community questions of Yahoo! Answers shows that a large proportion of opinion questions are IOQs. It is thus important to develop techniques to identify such questions. In this research, we first propose an effective framework based on mutual information and sequential pattern mining to construct an opinion lexicon that not only contains opinion words but also patterns. The discovered words and patterns are then combined with a machine learning technique to identify opinion questions. The experimental results on two datasets demonstrate the effectiveness of our approach.

Most approaches to semantics in computational linguistics represent meaning in terms of words or abstract symbols. Grounded-language research bases the meaning of natural language on perception and/or action in the (real or virtual) world. Machine learning has become the most effective approach to constructing natural-language systems; however, current methods require a great deal of laboriously annotated training data. Ideally, a computer would be able to acquire language like a child, by being exposed to language in the context of a relevant but ambiguous environment, thereby grounding its learning in perception and action. We will review recent research in grounded language learning and discuss future directions.

List of conference committees for AAAI-13, IAAI-13, and the EAAI-13 symposium.

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.

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.