Sampling-based robot motion planning: Towards realistic applications

This paper presents some of the recent improvements in sampling-based robot motion planning. Emphasis is placed on work that brings motion-planning algorithms closer to applicability in real environments. Methods that approach increasingly difficult motion-planning problems including kinodynamic motion planning and dynamic environments are discussed. The ultimate goal for such methods is to generate plans that can be executed with few modifications in a real robotics mobile platform.     

An additional condition for Bell experiments for accepting local realistic theories

We assume that one source of two uncorrelated spin-carrying particles emits them in a state, which can be described as a spin-1/2 bipartite pure uncorrelated state. We consider a Bell–Clauser–Horne–Shimony–Holt (Bell–CHSH) experiment with two-orthogonal-settings. We propose an additional condition for the state to be reproducible by the property of local realistic theories. We use the proposed measurement theory in order to construct the additional condition (Nagata and Nakamura in Int J Theor Phys 49:162, 2010). The condition is that local measurement outcome is $\pm 1/\sqrt{2}$ . Otherwise, such an experiment does not allow for the existence of local realistic theories even in the situation that all Bell–CHSH inequalities hold. Also we derive new set of Bell inequalities when local measurement outcome is $\pm 1/\sqrt{2}$ .     

Towards open ontology learning and filtering

Open ontology learning is the process of extracting a domain ontology from a knowledge source in an unsupervised way. Due to its unsupervised nature, it requires filtering mechanisms to rate the importance and correctness of the extracted knowledge. This paper presents OntoCmaps, a domain-independent and open ontology learning tool that extracts deep semantic representations from corpora. OntoCmaps generates rich conceptual representations in the form of concept maps and proposes an innovative filtering mechanism based on metrics from graph theory. Our results show that using metrics such as Betweenness, PageRank, Hits and Degree centrality outperforms the results of standard text-based metrics (TF-IDF, term frequency) for concept identification. We propose voting schemes based on these metrics that provide a good performance in relationship identification, which again provides better results (in terms of precision and F-measure) than other traditional metrics such as frequency of co-occurrences. The approach is evaluated against a gold standard and is compared to the ontology learning tool Text2Onto. The OntoCmaps generated ontology is more expressive than Text2Onto ontology especially in conceptual relationships and leads to better results in terms of precision, recall and F-measure.     

Layered learning design: Towards an integration of learning design and learning object perspectives

The use of ICT to enhance teaching and learning depends on effective design, which operates at many levels of granularity from the small to the very large. This reflects the range of educational problems from course design down to the design of activities focused on specific learning objectives. For maximum impact these layers of design need to be co-ordinated effectively. This paper delineates a reference model of ‘layered learning design’ where designs at one layer should use and incorporate designs from lower (more specific) layers in elegant and powerful ways. This would allow different designers, or tutors, to focus on different levels of abstraction in the learning design process, and to collaborate in combining designs to make a substantial impact on practice.     

Towards harnessing theories through tool support for hard real-time Java programming

We present a rationale for a selection of tools that assist developers of hard real-time applications to verify that programs conform to a Java real-time profile and that platform-specific resource constraints are satisfied. These tools are specialised instances of more generic static analysis and model checking frameworks. The concepts are illustrated by two case studies, and the strengths and the limitations of the tools are discussed.     

Probabilistic modelling, inference and learning using logical theories

This paper provides a study of probabilistic modelling, inference and learning in a logic-based setting. We show how probability densities, being functions, can be represented and reasoned with naturally and directly in higher-order logic, an expressive formalism not unlike the (informal) everyday language of mathematics. We give efficient inference algorithms and illustrate the general approach with a diverse collection of applications. Some learning issues are also considered.     

Inference of abduction theories for handling incompleteness in first-order learning

In real-life domains, learning systems often have to deal with various kinds of imperfections in data such as noise, incompleteness and inexactness. This problem seriously affects the knowledge discovery process, specifically in the case of traditional Machine Learning approaches that exploit simple or constrained knowledge representations and are based on single inference mechanisms. Indeed, this limits their capability of discovering fundamental knowledge in those situations. In order to broaden the investigation and the applicability of machine learning schemes in such particular situations, it is necessary to move on to more expressive representations which require more complex inference mechanisms. However, the applicability of such new and complex inference mechanisms, such as abductive reasoning, strongly relies on a deep background knowledge about the specific application domain. This work aims at automatically discovering the meta-knowledge needed to abduction inference strategy to complete the incoming information in order to handle cases of missing knowledge. Floriana Esposito received the Laurea degree in electronic Physics from the University of Bari, Italy, in 1970. Since 1994 is Full Professor of Computer Science at the University of Bari and Dean of the Faculty of Computer Science from 1997 to 2002. She founded and chairs the Laboratory for Knowledge Acquisition and Machine Learning of the Department of Computer Science. Her research activity started in the field of numerical models and statistical pattern recognition. Then her interests moved to the field of Artificial Intelligence and Machine Learning. The current research concerns the logical and algebraic foundations of numerical and symbolic methods in machine learning with the aim of the integration, the computational models of incremental and multistrategy learning, the revision of logical theories, the knowledge discovery in data bases. Application include document classification and understanding, content based document retrieval, map interpretation and Semantic Web. She is author of more than 270 scientific papers and is in the scientific committees of many international scientific Conferences in the field of Artificial Intelligence and Machine Learning. She co-chaired ICML96, MSL98, ECML-PKDD 2003, IEA-AIE 2005, ISMIS 2006. Stefano Ferilli was born in 1972. After receiving his Laurea degree in Information Science in 1996, he got a Ph.D. in Computer Science at the University of Bari in 2001. Since 2002 he is an Assistant Professor at the Department of Computer Science of the University of Bari. His research interests are centered on Logic and Algebraic Foundations of Machine Learning, Inductive Logic Programming, Theory Revision, Multi-Strategy Learning, Knowledge Representation, Electronic Document Processing and Digital Libraries. He participated in various National and European (ESPRIT and IST) projects concerning these topics, and is a (co-)author of more than 80 papers published on National and International journals, books and conferences/workshops proceedings. Teresa M.A. Basile got the Laurea degree in Computer Science at the University of Bari, Italy (2001). In March 2005 she discussed a Ph.D. thesis in Computer Science at the University of Bari titled “A Multistrategy Framework for First-Order Rules Learning.” Since April 2005, she is a research at the Computer Science Department of the University of Bari working on methods and techniques of machine learning for the Semantic Web. Her research interests concern the investigation of symbolic machine learning techniques, in particular of the cooperation of different inferences strategies in an incremental learning framework, and their application to document classification and understanding based on their semantic. She is author of about 40 papers published on National and International journals and conferences/workshops proceedings and was/is involved in various National and European projects. Nicola Di Mauro got the Laurea degree in Computer Science at the University of Bari, Italy. From 2001 he went on making research on machine learning in the Knowledge Acquisition and Machine Learning Laboratory (LACAM) at the Department of Computer Science, University of Bari. In March 2005 he discussed a Ph.D. thesis in Computer Science at the University of Bari titled “First Order Incremental Theory Refinement” which faces the problem of Incremental Learning in ILP. Since January 2005, he is an assistant professor at the Department of Computer Science, University of Bari. His research activities concern Inductive Logic Programming (ILP), Theory Revision and Incremental Learning, Multistrategy Learning, with application to Automatic Document Processing. On such topics HE is author of about 40 scientific papers accepted for presentation and publication on international and national journals and conference proceedings. He took part to the European projects 6th FP IP-507173 VIKEF (Virtual Information and Knowledge Environment Framework) and IST-1999-20882 COLLATE (Collaboratory for Annotation, Indexing and Retrieval of Digitized Historical Archive Materials), and to various national projects co-funded by the Italian Ministry for the University and Scientific Research.     

Towards more practical average bounds on supervised learning

In this paper, we describe a method which enables us to study the average generalization performance of learning directly via hypothesis testing inequalities. The resulting theory provides a unified viewpoint of average-case learning curves of concept learning and regression in realistic learning problems not necessarily within the Bayesian framework. The advantages of the theory are that it alleviates the practical pessimism frequently claimed for the results of the Vapnik-Chervonenkis (VC) theory and its alike, and provides general insights into generalization. Besides, the bounds on learning curves are directly related to the number of adjustable system weights. Although the theory is based on an approximation assumption, and cannot apply to the worst-case learning setting, the precondition of the assumption is mild, and the approximation itself is only a sufficient condition for the validity of the theory. We illustrate the results with numerical simulations, and apply the theory to examining the generalization ability of combination of neural networks.     

Towards learning a semantic-consistent subspace for cross-modal retrieval

A great many of approaches have been developed for cross-modal retrieval, among which subspace learning based ones dominate the landscape. Concerning whether using the semantic label information or not, subspace learning based approaches can be categorized into two paradigms, unsupervised and supervised. However, for multi-label cross-modal retrieval, supervised approaches just simply exploit multi-label information towards a discriminative subspace, without considering the correlations between multiple labels shared by multi-modalities, which often leads to an unsatisfactory retrieval performance. To address this issue, in this paper we propose a general framework, which jointly incorporates semantic correlations into subspace learning for multi-label cross-modal retrieval. By introducing the HSIC-based regularization term, the correlation information among multiple labels can be not only leveraged but also the consistency between the modality similarity from each modality is well preserved. Besides, based on the semantic-consistency projection, the semantic gap between the low-level feature space of each modality and the shared high-level semantic space can be balanced by a mid-level consistent one, where multi-label cross-modal retrieval can be performed effectively and efficiently. To solve the optimization problem, an effective iterative algorithm is designed, along with its convergence analysis theoretically and experimentally. Experimental results on real-world datasets have shown the superiority of the proposed method over several existing cross-modal subspace learning methods.

     

Advanced computational models and learning theories for spoken language processing

Recent developments in research on humanoid robots and interactive agents have highlighted the importance of and expectation on automatic speech recognition (ASR) as a means of endowing such an agent with the ability to communicate via speech. This article describes some of the approaches pursued at NTT Communication Science Laboratories (NTT-CSL) for dealing with such challenges in ASR. In particular, we focus on methods for fast search through finite-state machines, Bayesian solutions for modeling and classification of speech, and a discriminative training approach for minimizing errors in large vocabulary continuous speech recognition.     

Integration of reinforcement learning and optimal decision-making theories of the basal ganglia

This article seeks to integrate two sets of theories describing action selection in the basal ganglia: reinforcement learning theories describing learning which actions to select to maximize reward and decision-making theories proposing that the basal ganglia selects actions on the basis of sensory evidence accumulated in the cortex. In particular, we present a model that integrates the actor-critic model of reinforcement learning and a model assuming that the cortico-basal-ganglia circuit implements a statistically optimal decision-making procedure. The values of cortico-striatal weights required for optimal decision making in our model differ from those provided by standard reinforcement learning models. Nevertheless, we show that an actor-critic model converges to the weights required for optimal decision making when biologically realistic limits on synaptic weights are introduced. We also describe the model's predictions concerning reaction times and neural responses during learning, and we discuss directions required for further integration of reinforcement learning and optimal decision-making theories.     

A Semantic Web-based authoring tool to facilitate the planning of collaborative learning scenarios compliant with learning theories

When the goal of group activities is to support long-term learning, the task of designing well-thought-out collaborative learning (CL) scenarios is an important key to success. To help students adequately acquire and develop their knowledge and skills, a teacher can plan a scenario that increases the probability for learning to occur. Such a scenario defines pedagogically sound structures that prevent off-task behavior and engage students in more meaningful interactions. The main difficulty in designing effective CL scenarios is transforming the teacher's intentions into elements that constitute the learning scenario. This problem is frequently observed when novice teachers attempt to improve the quality of learning and instruction by blending collaborative activities with individual activities without careful planning. With the goal of helping teachers in planning collaborative scenarios, we have developed an intelligent authoring tool referred to as CHOCOLATO using Semantic Web technologies (e.g. ontologies) in order to represent knowledge about different pedagogies and practices related to collaboration. Through the use of this knowledge, CHOCOLATO can provide intelligent guidance that helps teachers to create theory-based CL scenarios which has proven to be effective in a variety of situations. We evaluated it by conducting two experiments. We were interested in verifying whether the recommendations given by CHOCOLATO help novice teachers to design pedagogically sound CL activities, and if these activities help students to learn collaboratively in real classroom settings. The first experiment had the participation of 58 pre-service teachers that created CL scenarios with and without our authoring tool and the second experiment was carried out in a Brazilian public school together with 218 students. The results suggest that the guidance provided by CHOCOLATO do help novice teachers plan, understand and share CL scenarios more easily. They also suggest that the continuous utilization of well-designed theory-based CL activities create favorable conditions for students (particularly less knowledgeable ones) to improve their overall performance throughout the school year.     

Towards a unified multi-source-based optimization framework for multi-label learning

In the era of Big Data, a practical yet challenging task is to make learning techniques more universally applicable in dealing with the complex learning problem, such as multi-source multi-label learning. While some of the early work have developed many effective solutions for multi-label classification and multi-source fusion separately, in this paper we learn the two problems together, and propose a novel method for the joint learning of multiple class labels and data sources, in which an optimization framework is constructed to formulate the learning problem, and the result of multi-label classification is induced by the weighted combination of the decisions from multiple sources. The proposed method is responsive in exploiting the label correlations and fusing multi-source data, especially in the fusion of long-tail data. Experiments on various multi-source multi-label data sets reveal the advantages of the proposed method.     

Towards optimal software engineering: learning from agile practice

In essence, optimal software engineering means creating the right product, through the right process, to the overall satisfaction of everyone involved. Adopting the agile approach to software development appears to have helped many companies make substantial progress towards that goal. The purpose of this paper is to clarify that contribution from comparative survey information gathered in 2010 and 2012. The surveys were undertaken in software development companies across Northern Ireland. The paper describes the design of the surveys and discusses optimality in relation to the results obtained. Both surveys aimed to achieve comprehensive coverage of a single region rather than rely on a voluntary sample. The main outcome from the work is a collection of insights into the nature and advantages of agile development, suggesting how further progress towards optimality might be achieved.     

Towards learner-constructed e-learning environments for effective personal learning experiences

Whilst a lot of research has been carried out on designing learning environments to meet the needs of learners, much of such research has focused on producing less flexible ready-made environments for learners to interact with. However, e-learning design and development could benefit from the lessons of the interaction of users with mobile devices, where users interact by selecting applications (Apps) they are interested in and hence engage with the device in an addictive way. By transposing the same interaction idea to the e-learning environment, if given the opportunity, learners will construct an environment that meets their needs with the tools that are available and hence will be motivated to engage more with such environment, possibly leading to improved performance. This article proposes FAUCLE (Flexible and Accessible User Constructed Learning Environment), a learner-centred model for a learner-constructed learning environment. It is hoped that this paper will encourage research interest on innovative ways of designing learner-centred learning environments that encourage active and inclusive learning.     

Learning sensory maps with real-world stimuli in real time using abiophysically realistic learning rule

We present a real-time model of learning in the auditory cortex that is trained using real-world stimuli. The system consists of a peripheral and a central cortical network of spiking neurons. The synapses formed by peripheral neurons on the central ones are subject to synaptic plasticity. We implemented a biophysically realistic learning rule that depends on the precise temporal relation of pre- and postsynaptic action potentials. We demonstrate that this biologically realistic real-time neuronal system forms stable receptive fields that accurately reflect the spectral content of the input signals and that the size of these representations can be biased by global signals acting on the local learning mechanism. In addition, we show that this learning mechanism shows fast acquisition and is robust in the presence of large imbalances in the probability of occurrence of individual stimuli and noise.     

Towards deeper learning through creativity within online communities in primary education

Despite recent British government moves to equip all Primary Schools with fast broadband connections to the Internet, it would seem that many schools as yet make little use of the increased capacity this affords other than to incorporate more and more rich multimedia in the form of interactive games or animated presentations to illustrate particular concepts or practise specific skills. Whilst not wanting to deny the potential and value of such activities, this paper will focus on the potential use of online communities to reverse this rather unidirectional relationship children often experience with the Internet. That is, the potential within online communities to facilitate a more reciprocal relationship as children become benefactors as well as recipients of the wealth of web-based information, and the quality of learning that may ensue.     

Towards gesture-based programming: shape from motion primordial learning of sensorimotor primitives

Gesture-based programming (GBP) is a paradigm for the evolutionary programming of dextrous robotic systems by human demonstration. We call the paradigm “gesture-based” because we try to capture, in real-time, the intention behind the demonstratrator's fleeting, context-dependent hand motions, contact conditions, finger poses, and even cryptic utterances, rather than just recording and replaying movement. The paradigm depends on a pre-existing knowledge base of capabilities, collectively called “encapsulated expertise”, that comprise the real-time sensorimotor primitives from which the run-time executable is constructed as well as providing the basis for interpreting the teacher's actions during programming. In this paper we first describe the GBP environment, which is not fully implemented. We then present a technique based on principal components analysis, augmentable with model-based information, for learing and recognizing sensorimotor primitives. This paper describes simple applications of the technique to a small mobile robot and a PUMA manipulator. The mobile robot learned to escape from jams while the manipulator learned guarded moves and rotational accommodation that are composable to allow flat plate mating operations. While these initial applications are simple, they demonstrate the ability to extract primitives from demonstration, recognize the learned primitives in subsequent demonstrations, and combine and transform primitives to create different capabilities, which are all critical to the GBP paradigm.