Learning task specific distributed paragraph representations using a 2-tier convolutional neural network

We introduce a type of 2-tier convolutional neural network model for learning distributed paragraph representations for a special task (e.g. paragraph or short document level sentiment analysis and text topic categorization). We decompose the paragraph semantics into 3 cascaded constitutes: word representation, sentence composition and document composition. Specifically, we learn distributed word representations by a continuous bag-of-words model from a large unstructured text corpus. Then, using these word representations as pre-trained vectors, distributed task specific sentence representations are learned from a sentence level corpus with task-specific labels by the first tier of our model. Using these sentence representations as distributed paragraph representation vectors, distributed paragraph representations are learned from a paragraph-level corpus by the second tier of our model. It is evaluated on DBpedia ontology classification dataset and Amazon review dataset. Empirical results show the effectiveness of our proposed learning model for generating distributed paragraph representations.

Learning to be different:heterogeneity and efficiency in distributed smart camera networks

In this paper we study the self-organising behaviour of smart camera networks which use market-based handover of object tracking responsibilities to achieve an efficient allocation of objects to cameras. Specifically, we compare previously known homogeneous configurations, when all cameras use the same marketing strategy, with heterogeneous configurations, when each camera makes use of its own, possibly different marketing strategy. Our first contribution is to establish that such heterogeneity of marketing strategies can lead to system wide outcomes which are Pareto superior when compared to those possible in homogeneous configurations. However, since the particular configuration required to lead to Pareto efficiency in a given scenario will not be known in advance, our second contribution is to show how online learning of marketing strategies at the individual camera level can lead to high performing heterogeneous configurations from the system point of view, extending the Pareto front when compared to the homogeneous case. Our third contribution is to show that in many cases, the dynamic behaviour resulting from online learning leads to global outcomes which extend the Pareto front even when compared to static heterogeneous configurations. Our evaluation considers results obtained from an open source simulation package as well as data from a network of real cameras. © 2013 IEEE.

Learning user and product distributed representations using a sequence model for sentiment analysis

In product reviews, it is observed that the distribution of polarity ratings over reviews written by different users or evaluated based on different products are often skewed in the real world. As such, incorporating user and product information would be helpful for the task of sentiment classification of reviews. However, existing approaches ignored the temporal nature of reviews posted by the same user or evaluated on the same product. We argue that the temporal relations of reviews might be potentially useful for learning user and product embedding and thus propose employing a sequence model to embed these temporal relations into user and product representations so as to improve the performance of document-level sentiment analysis. Specifically, we first learn a distributed representation of each review by a one-dimensional convolutional neural network. Then, taking these representations as pretrained vectors, we use a recurrent neural network with gated recurrent units to learn distributed representations of users and products. Finally, we feed the user, product and review representations into a machine learning classifier for sentiment classification. Our approach has been evaluated on three large-scale review datasets from the IMDB and Yelp. Experimental results show that: (1) sequence modeling for the purposes of distributed user and product representation learning can improve the performance of document-level sentiment classification; (2) the proposed approach achieves state-of-The-Art results on these benchmark datasets.

Load–frequency control : a GA-based multi-agent reinforcement learning

The load–frequency control (LFC) problem has been one of the major subjects in a power system. In practice, LFC systems use proportional–integral (PI) controllers. However since these controllers are designed using a linear model, the non-linearities of the system are not accounted for and they are incapable of gaining good dynamical performance for a wide range of operating conditions in a multi-area power system. A strategy for solving this problem because of the distributed nature of a multi-area power system is presented by using a multi-agent reinforcement learning (MARL) approach. It consists of two agents in each power area; the estimator agent provides the area control error (ACE) signal based on the frequency bias estimation and the controller agent uses reinforcement learning to control the power system in which genetic algorithm optimisation is used to tune its parameters. This method does not depend on any knowledge of the system and it admits considerable flexibility in defining the control objective. Also, by finding the ACE signal based on the frequency bias estimation the LFC performance is improved and by using the MARL parallel, computation is realised, leading to a high degree of scalability. Here, to illustrate the accuracy of the proposed approach, a three-area power system example is given with two scenarios.

Learning spatial concepts from RatSLAM representations

RatSLAM is a biologically-inspired visual SLAM and navigation system that has been shown to be effective indoors and outdoors on real robots. The spatial representation at the core of RatSLAM, the experience map, forms in a distributed fashion as the robot learns the environment. The activity in RatSLAM’s experience map possesses some geometric properties, but still does not represent the world in a human readable form. A new system, dubbed RatChat, has been introduced to enable meaningful communication with the robot. The intention is to use the “language games” paradigm to build spatial concepts that can be used as the basis for communication. This paper describes the first step in the language game experiments, showing the potential for meaningful categorization of the spatial representations in RatSLAM.

Levels of awareness of professional ethics used as a sensitizing method in project-based learning

There is a need for educational frameworks for computer ethics education. This discussion paper presents an approach to developing students’ moral sensitivity, an awareness of morally relevant issues, in project-based learning (PjBL). The proposed approach is based on a study of IT professionals’ levels of awareness of ethics. These levels are labelled My world, The corporate world, A shared world, The client’s world and The wider world. We give recommendations for how instructors may stimulate students’ thinking with the levels and how the levels may be taken into account in managing a project course and in an IS department. Limitations of the recommendations are assessed and issues for discussion are raised.

Ezine and iRadio as knowledge creation metaphors for scaffolding learning in physical and virtual learning spaces

eZine and iRadio represent metaphors for multimedia communication on the Internet. Participating students experience a simulated Internet publishing environment in both their classroom and virtual learning environment. This chapter presents an autoethnographic account highlighting the voices of the learning designer and the teacher and provides evidence of the planning and implementation of two tertiary music elective courses over three iterations of each course. A blended learning environment was incorporated within each elective music course and a collaborative approach to development between lecturers, tutors, learning and technological designers using an iterative research design. The research suggests that learning design which provides real world examples and resources integrating authentic task design into their unit can provide meaningful and engaging experiences for students. The dialogue between learning designers and teachers and iterative review of the learning process and student outcomes, we believe, has engaged students meaningfully to achieve transferable learning outcomes.

Multitask learning with expert advice

We consider the problem of prediction with expert advice in the setting where a forecaster is presented with several online prediction tasks. Instead of competing against the best expert separately on each task, we assume the tasks are related, and thus we expect that a few experts will perform well on the entire set of tasks. That is, our forecaster would like, on each task, to compete against the best expert chosen from a small set of experts. While we describe the "ideal" algorithm and its performance bound, we show that the computation required for this algorithm is as hard as computation of a matrix permanent. We present an efficient algorithm based on mixing priors, and prove a bound that is nearly as good for the sequential task presentation case. We also consider a harder case where the task may change arbitrarily from round to round, and we develop an efficient approximate randomized algorithm based on Markov chain Monte Carlo techniques.

Emergent task-specific object semantics through distributed experience networks

Autonomous development of sensorimotor coordination enables a robot to adapt and change its action choices to interact with the world throughout its lifetime. The Experience Network is a structure that rapidly learns coordination between visual and haptic inputs and motor action. This paper presents methods which handle the high dimensionality of the network state-space which occurs due to the simultaneous detection of multiple sensory features. The methods provide no significant increase in the complexity of the underlying representations and also allow emergent, task-specific, semantic information to inform action selection. Experimental results show rapid learning in a real robot, beginning with no sensorimotor mappings, to a mobile robot capable of wall avoidance and target acquisition.

Leading the transformation of learning and praxis in science classrooms

Individual science teachers who have inspired colleagues to transform their classroom praxis have been labelled transformational leaders. As the notion of distributed leadership became more accepted in the educational literature, the focus on the individual teacher-leader shifted to the study of leadership praxis both by individuals (whoever they might be) and by collectives within schools and science classrooms. This review traces the trajectory of leadership research, in the context of learning and teaching science, from an individual focus to a dialectical relationship between individual and collective praxis. The implications of applying an individual-collective perspective to praxis for teachers, students and their designated leaders are discussed.

A comparison of methods for classifying clinical samples based on proteomics data : a case study for statistical and machine learning approaches

The discovery of protein variation is an important strategy in disease diagnosis within the biological sciences. The current benchmark for elucidating information from multiple biological variables is the so called “omics” disciplines of the biological sciences. Such variability is uncovered by implementation of multivariable data mining techniques which come under two primary categories, machine learning strategies and statistical based approaches. Typically proteomic studies can produce hundreds or thousands of variables, p, per observation, n, depending on the analytical platform or method employed to generate the data. Many classification methods are limited by an n≪p constraint, and as such, require pre-treatment to reduce the dimensionality prior to classification. Recently machine learning techniques have gained popularity in the field for their ability to successfully classify unknown samples. One limitation of such methods is the lack of a functional model allowing meaningful interpretation of results in terms of the features used for classification. This is a problem that might be solved using a statistical model-based approach where not only is the importance of the individual protein explicit, they are combined into a readily interpretable classification rule without relying on a black box approach. Here we incorporate statistical dimension reduction techniques Partial Least Squares (PLS) and Principal Components Analysis (PCA) followed by both statistical and machine learning classification methods, and compared them to a popular machine learning technique, Support Vector Machines (SVM). Both PLS and SVM demonstrate strong utility for proteomic classification problems.

Listening skill requires a further look into second/foreign language learning

Current English-as-a-second and foreign-language (ESL/EFL) research has encouraged to treat each communicative macroskill separately due to space constraint, but the interrelationship among these skills (listening, speaking, reading, and writing) is not paid due attention. This study attempts to examine first the existing relationship among the four dominant skills, second the potential impact of reading background on the overall language proficiency, and finally the relationship between listening and overall language proficiency as listening is considered an overlooked/passive skill in the pedagogy of the second/foreign language classroom. However, the literature in language learning has revealed that listening skill has salient importance in both first and second language learning. The purpose of this study is to investigate the role of each of four skills in EFL learning and their existing interrelationships in an EFL setting. The outcome of 701 Iranian applicants undertaking International English Language Testing System (IELTS) in Tehran demonstrates that all communicative macroskills have varied correlations from moderate (reading and writing) to high (listening and reading). The findings also show that the applicants’ reading history assisted them in better performing at high stakes tests, and what is more, listening skill was strongly correlated with the overall language proficiency.

Towards visualising people’s ecology of hybrid personal learning environments

Ambient media architecture can provide place-based collaborative learning experiences and pathways for social interactions that would not be otherwise possible. This paper is concerned with ways of enhancing peer-to-peer learning affordances in library spaces; how can the library facilitate the community of library users to learn from each other? We report on the findings of a study that employed a participatory design method where participants were asked to reflect and draw places, social networks, and activities that they use to work (be creative, productive), play (have fun, socialize, be entertained), and learn (acquire new information, knowledge, or skills). The results illustrate how informal learning – learning outside the formal education system – is facilitated by a personal selection of physical and socio-cultural environments, as well as online tools, platforms, and networks. This paper sheds light on participants’ individually curated ecologies of their work, play, and learning related networks and the hybrid (physical and digital) nature of these places. These insights reveal opportunities for ambient media architecture to increase awareness of and connections between people’s hybrid personal learning environments.

Increasing learners’ satisfaction/intention to adopt more e-learning

Purpose: E-learning is an organisationally risky investment given the cost and poor levels of adoption by users. In order to gain a better understanding of this problem, a study was conducted into the use of e-learning in a rail organisation. Design/methodology/approach: Using an online survey, employees of a rail-sector organisation were questioned about their use and likelihood of adoption of e-learning. This study explores the factors that affect the way in which learners experience and perceive such systems. Using statistical analysis, twelve hypotheses are tested and explored. Relationships between learning satisfaction, intention to adopt and the characteristics of e-learning systems were established. Findings: The study found that e-learning characteristics can buffer the relationship between learner characteristics and intention to adopt further e-learning in the future. Further, we found that high levels of support can compensate individuals who are low in technological efficacy to adopt e-learning. Research limitations/implications: The cross-sectional design of the study and its focus on measuring intention to adopt as opposed to actual adoption are both limitations. Future research using longitudinal design and research employing a time lag design measuring actual adoption as well as intention are recommended. Practical implications: From a practical perspective, organizations can focus on the actual content and authenticity of the learning experience delivered by the e-learning system to significantly impact how employees will perceive and use e-learning in the future. Low technological efficacy individuals tend not to adopt new technology. Instead of changing individuals’ personalities, organizations can implement supportive policies and practices which would lead to higher e-learning adoption rate among low efficacy individuals. Originality/value: The study integrates technology adoption and learning literatures in developing enablers for e-learning in organizations. Further, this study collects data from rail employees, and therefore the findings are practical to an industry.