Abstract

Recent work on Acoustic Unit Discovery (AUD) has led to the development of a non-parametric Bayesian phone-loop model where the prior over the probability of the phone-like units is assumed to be sampled from a Dirichlet Process (DP). In this work, we propose to improve this model by incorporating a Hierarchical Pitman-Yor based bigram Language Model on top of the units' transitions. This new model makes use of the phonotactic context information but assumes a fixed number of units. To remedy this limitation we first train a DP phone-loop model to infer the number of units, then, the bigram phone-loop is initialized from the DP phone-loop and trained until convergence of its parameters. Results show an absolute improvement of 1–2%on the Normalized Mutual Information (NMI) metric. Furthermore, we show that, combined with Multilingual Bottleneck (MBN) features the model yields a same or higher NMI as an English phone recogniser trained on TIMIT.

Abstract

With immense amount of data growing on web in Hindi, a text summariser would be helpful in summarising Government data, medical reports, news, and research articles. Hindi is the fourth most-spoken first language in the world. Hindi written in the Devanagari script is the official language of the Government of India. There is no public dataset for extractive summarisation available in Hindi and thus a dataset of 24253 News articles was extracted and the extractive summaries results were evaluated on various parameters with manual gold summaries of exactly 60 words each.

Abstract

Data structures is an important area of knowledge in computer science that is often difficult to understand for high school students. There has been a lot of research in computer science education around the subject of programming. Hence, it becomes imperative to explore the domain of data structures as well. With this work, we have looked into an active pedagogical approach for facilitating learning of data structures in school. This approach has been implemented by means of an interactive game. The game aims to teach arrays and linked lists through activities based on the principle of compare and contrast. The innovation in the game is the use of musical notes to teach operations in arrays and linked lists. The game was evaluated with 27 students across 8th, 9th and 10th grades using a questionnaire. The results of the evaluation showed that the group of students who learnt about arrays and linked lists through the game scored an average of 81.5% of the total marks while the other group scored an average of 72% of the total marks.

Abstract

Mobile devices are gaining prominence for a variety of activities. From casual browsing to complex tasks like online shopping and banking, people have started using mobiles for almost everything previously done on a desktop. As more and more tasks are shifting towards mobiles, it has become crucial to redesign desktop elements to fit and function consistently on mobile devices as well. One such element is data visualization. The process of designing visualizations for desktops is fairly matured; however, when it comes to mobile devices there are still a number of challenges faced. Most of these challenges revolve around the limited screen space and fewer conventional mediums of interactions offered by these devices. This paper presents a set of design patterns that help overcome some of the challenges faced when designing data visualizations. These patterns are designed for line charts on mobile devices. However, some of them might apply to other kinds of charts as well. There are four patterns presented in this paper, namely details slider, legend filter, selection brush, and responsive data grid. These patterns can be used either individually or together to help make visualizations more convenient to use on mobile devices.

Abstract

Predicting the outcome of a match has always been at the center of sports analytics. Indian Premier League (IPL), a professional Twenty20 (T20) cricket league in India, has established itself as one of the biggest tournaments in cricket history. In this paper, we propose a model to predict the winner at the end of each over in the second innings of an IPL cricket match. Our methodology not only incorporates the dynamically updating game context as the game progresses, but also includes the relative strength between the two teams playing the match. Estimating the relative strength between two teams involves modeling the individual participating players’ potentials. To model a player, we use his career as well as recent performance statistics. Using the various dynamic features, we evaluate several supervised learning algorithms to predict the winner of the match. Finally, using the Random Forest Classifier (RFC), we have achieved an accuracy of 65.79% - 84.15% over the course of second innings, with an overall accuracy of 75.68%.

Abstract

Query recommendation (QR) support search engine to provide alternative queries as a recommendation using similarity-based approaches. In the literature, orthogonal query recommendation (OQR) has been proposed to compute the diversity of QR when the user does not formulate proper queries. The OQR uses dissimilarity measure in QR to recommend completely different queries. In this paper, we propose an approach in QR by extending association rules, diverse patterns, and unbalanced concept hierarchy of search terms. We conceptualize association rules based QR, and order the rules based on confidence and diversity. Subsequently, the high ranked rules based on confidence and diversity are provided in QRs. The experimental results on real world AOL click-through dataset show that the diverse QRs improve the performance significantly

Abstract

The architectural trend towards heterogeneity has pushed heterogeneous computing to the fore of parallel computing research. Heterogeneous algorithms, often carefully handcrafted, have been designed for several important problems from parallel computing such as sorting, graph algorithms, matrix computations, and the like. A majority of these algorithms follow a work partitioning approach where the input is divided into appropriate sized parts so that individual devices can process the “right-sized” parts of the input. However, arriving at a good work partitioning is usually non-trivial and may crucially depend also on the input instance apart from the heterogeneous algorithm used. An extensive empirical search is not helpful as such an empirical search can potentially offset any gains accrued out of heterogeneous algorithms. Other recently proposed approaches too are in general inadequate. In this paper, we propose a simple and effective technique for work partitioning in the context of heterogeneous algorithms. Our technique is based on randomized sampling and therefore can adapt to both the algorithm used and the input instance. Our technique is generic in its applicability as we will demonstrate in this paper. We validate our technique on three problems: multiplying two unstructured sparse matrices (spmm), multiplying two scale-free sparse matrices, and finding the connected components of a graph (CC). For these problems, we show that using our method, we can find the required threshold that is under 10% away from the best possible thresholds respectively.

Abstract

What makes a computational neuronal model ’large scale’ ? Is it the number of neurons modeled? Or the number of brain regions modeled in a network? Most of the higher cognitive processes span across co-ordinated activity in a network of different brain areas. However at the same time, the basic information transfer takes place at a single neuron level, together with multiple other neurons. We explore modeling a neural system involving some areas of cortex, the basal ganglia (BG) and thalamus for the process of decision making, using a largescale neural engineering framework, Nengo. Early results tend to replicate the known neural activity patterns as found in the previous action selection model by Guthrie et al. 2013, besides operating with a larger neuronal populations. The power of converting algorithms to efficiently weighed neural networks in Nengo (Stewart et al. 2009 and Bekolay et al. 2013) is exploited in this work. Crucial aspects in a computational model, like parameter tuning and detailed neural implementations, while moving from a simplistic to large-scale model, are studied.

Abstract

We assess change in metastability to characterize age-effects on the dynamic repertoire of the functional networks at rest. Resting state fMRI signals from each subject (N=48) have been used and metastability is evaluated as the standard deviation of mean phase synchrony of BOLD signals across whole-brain as well as across known resting state networks. The results suggest that significant whole-brain metastability changes occur between middle to old age. We also demonstrate that static time-averaged FC largely undermines age-effects on the interaction between functional networks. Discriminant Function Analysis reveals existence of two different patterns of change in metastability, which maximally discriminates between two different processes of maturation and ageing.

Abstract

In this research paper, noise suppression ability of associative memories (e.g. Hopfield neural network) is briefly summarized. Motivated by this fact, noise suppression abilities of trained convolutional network is discussed. Introducing the concept of null vectors, noise suppression ability of Single Layer Perceptron, Multi-Layer Perceptron and Extreme Learning Machine are discussed.