Online learning of autonomous helicopter control

This paper details the development of an online adaptive control system, designed to learn from the actions of an instructing pilot. Three learning architectures, single layer neural networks (SLNN), multi-layer neural networks (MLNN), and fuzzy associative memories (FAM) are considerd. Each method has been tested in simulation. While the SLNN and MLNN provided adequate control under some simulation conditions, the addition of pilot noise and pilot variation during simulation training caused these methods to fail.

Crossing literacy and informed learning boundaries with Manga

This research investigated high school students’ experiences of informed learning in a literacy development workshop. It was conducted in the library of an Australian high school with a low socio-economic population. Building upon students’ fascination with Manga fiction and artwork, the workshop was part of a larger university-community engagement project Crossing Boundaries with Reading which aimed to address widespread literacy challenges at the school. The paper first provides a brief literature review that introduces the concept of informed learning, or the experience of using information to learn. In practice, informed learning fosters simultaneous learning about using information and learning about a topic. Thus, information is a transformative force that extends beyond functional information literacy skills. Then, the paper outlines the phenomenographic methodology used in this study, the workshop context and the research participants. The findings reveal three different ways that students experienced the workshop: as an art lesson; as a life lesson; and as an informed learning lesson. The discussion highlights the power of informed learning as a holistic approach to information literacy education. The study’s findings are significant as students from low socio-economic backgrounds are often at risk of experiencing disadvantage throughout their lives if they do not develop a range of literacies including the ability to use information effectively. Responding to this problem, the paper provides an empirically-based example of informed learning to support further research and develop professional practice. While the research context is limited to one high school library, the findings are of potential value for teacher-librarians, educators and information professionals elsewhere.

Resolving Ambiguities in Confused Online Tamil Characters with Post Processing Algorithms

This paper addresses the problem of resolving ambiguities in frequently confused online Tamil character pairs by employing script specific algorithms as a post classification step. Robust structural cues and temporal information of the preprocessed character are extensively utilized in the design of these algorithms. The methods are quite robust in automatically extracting the discriminative sub-strokes of confused characters for further analysis. Experimental validation on the IWFHR Database indicates error rates of less than 3 % for the confused characters. Thus, these post processing steps have a good potential to improve the performance of online Tamil handwritten character recognition.

An Estimator Algorithm For Learning Automata With Changing Number Of Actions

In many problems of decision making under uncertainty the system has to acquire knowledge of its environment and learn the optimal decision through its experience. Such problems may also involve the system having to arrive at the globally optimal decision, when at each instant only a subset of the entire set of possible alternatives is available. These problems can be successfully modelled and analysed by learning automata. In this paper an estimator learning algorithm, which maintains estimates of the reward characteristics of the random environment, is presented for an automaton with changing number of actions. A learning automaton using the new scheme is shown to be e-optimal. The simulation results demonstrate the fast convergence properties of the new algorithm. The results of this study can be extended to the design of other types of estimator algorithms with good convergence properties.

Two-timescale Q-learning Algorithms with an Application to Routing in Networks

We propose two variants of the Q-learning algorithm that (both) use two timescales. One of these updates Q-values of all feasible state-action pairs at each instant while the other updates Q-values of states with actions chosen according to the ‘current ’ randomized policy updates. A sketch of convergence of the algorithms is shown. Finally, numerical experiments using the proposed algorithms for routing on different network topologies are presented and performance comparisons with the regular Q-learning algorithm are shown.

A novel Q-learning algorithm with function approximation for constrained Markov decision processes

We present a novel multi-timescale Q-learning algorithm for average cost control in a Markov decision process subject to multiple inequality constraints. We formulate a relaxed version of this problem through the Lagrange multiplier method. Our algorithm is different from Q-learning in that it updates two parameters - a Q-value parameter and a policy parameter. The Q-value parameter is updated on a slower time scale as compared to the policy parameter. Whereas Q-learning with function approximation can diverge in some cases, our algorithm is seen to be convergent as a result of the aforementioned timescale separation. We show the results of experiments on a problem of constrained routing in a multistage queueing network. Our algorithm is seen to exhibit good performance and the various inequality constraints are seen to be satisfied upon convergence of the algorithm.

A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching

Cross domain and cross-modal matching has many applications in the field of computer vision and pattern recognition. A few examples are heterogeneous face recognition, cross view action recognition, etc. This is a very challenging task since the data in two domains can differ significantly. In this work, we propose a coupled dictionary and transformation learning approach that models the relationship between the data in both domains. The approach learns a pair of transformation matrices that map the data in the two domains in such a manner that they share common sparse representations with respect to their own dictionaries in the transformed space. The dictionaries for the two domains are learnt in a coupled manner with an additional discriminative term to ensure improved recognition performance. The dictionaries and the transformation matrices are jointly updated in an iterative manner. The applicability of the proposed approach is illustrated by evaluating its performance on different challenging tasks: face recognition across pose, illumination and resolution, heterogeneous face recognition and cross view action recognition. Extensive experiments on five datasets namely, CMU-PIE, Multi-PIE, ChokePoint, HFB and IXMAS datasets and comparisons with several state-of-the-art approaches show the effectiveness of the proposed approach. (C) 2015 Elsevier B.V. All rights reserved.

A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching

Cross domain and cross-modal matching has many applications in the field of computer vision and pattern recognition. A few examples are heterogeneous face recognition, cross view action recognition, etc. This is a very challenging task since the data in two domains can differ significantly. In this work, we propose a coupled dictionary and transformation learning approach that models the relationship between the data in both domains. The approach learns a pair of transformation matrices that map the data in the two domains in such a manner that they share common sparse representations with respect to their own dictionaries in the transformed space. The dictionaries for the two domains are learnt in a coupled manner with an additional discriminative term to ensure improved recognition performance. The dictionaries and the transformation matrices are jointly updated in an iterative manner. The applicability of the proposed approach is illustrated by evaluating its performance on different challenging tasks: face recognition across pose, illumination and resolution, heterogeneous face recognition and cross view action recognition. Extensive experiments on five datasets namely, CMU-PIE, Multi-PIE, ChokePoint, HFB and IXMAS datasets and comparisons with several state-of-the-art approaches show the effectiveness of the proposed approach. (C) 2015 Elsevier B.V. All rights reserved.

l(1)-K-SVD: A robust dictionary learning algorithm with simultaneous update

We develop a new dictionary learning algorithm called the l(1)-K-svp, by minimizing the l(1) distortion on the data term. The proposed formulation corresponds to maximum a posteriori estimation assuming a Laplacian prior on the coefficient matrix and additive noise, and is, in general, robust to non-Gaussian noise. The l(1) distortion is minimized by employing the iteratively reweighted least-squares algorithm. The dictionary atoms and the corresponding sparse coefficients are simultaneously estimated in the dictionary update step. Experimental results show that l(1)-K-SVD results in noise-robustness, faster convergence, and higher atom recovery rate than the method of optimal directions, K-SVD, and the robust dictionary learning algorithm (RDL), in Gaussian as well as non-Gaussian noise. For a fixed value of sparsity, number of dictionary atoms, and data dimension, l(1)-K-SVD outperforms K-SVD and RDL on small training sets. We also consider the generalized l(p), 0 < p < 1, data metric to tackle heavy-tailed/impulsive noise. In an image denoising application, l(1)-K-SVD was found to result in higher peak signal-to-noise ratio (PSNR) over K-SVD for Laplacian noise. The structural similarity index increases by 0.1 for low input PSNR, which is significant and demonstrates the efficacy of the proposed method. (C) 2015 Elsevier B.V. All rights reserved.

Broadland Council Training Services – Winning your e-Learning Spurs with Xerte/Maxos

Broadland Council Training Services have reined in their reliance on traditional learning methods by introducing Xerte/Maxos to their equine-based students. Learners who were once deluged by stacks of paper and unable to utilise an internet connection in a horse yard are now able to access interactive learning exercises using Maxos: Xerte on a memory stick. Students are now more engaged and focused on their studies, teaching methods are much more diverse, and success rates have improved.

Online Learning Readiness Tool Guide

A user guide for the Online Learning Readiness Tool, developed as part of the Jisc Scaling up online learning project.