Growth of Motor Coordination in Early Robot Learning

M. H. Lee and Q. Meng, Growth of Motor Coordination in Early Robot Learning, IJCAI-05, 2005.

Novelty and Habituation: the Driving Forces in Early Stage Learning for Developmental Robotics

Q. Meng and M. H. Lee, Novelty and Habituation: the Driving Forces in Early Stage Learning for Developmental Robotics, AI-Workshop on NeuroBotics, University of Ulm, Germany. September 2004.

A dichotomic search algorithm for mining and learning in domain-specific logics

Ferr?, S. and King, R. D. (2004) A dichotomic search algorithm for mining and learning in domain-specific logics. Fundamenta Informaticae. IOS Press. To appear

JUSTEIS: JISC Usage Surveys: Trends in Electronic Information Services Final report 2003/2004 Cycle Five

Urquhart, C., Spink, S., Thomas, R., Yeoman, A., Durbin, J., Turner, J., Fenton, R. & Armstrong, C. (2004). JUSTEIS: JISC Usage Surveys: Trends in Electronic Information Services Final report 2003/2004 Cycle Five. Aberystwyth: Department of Information Studies, University of Wales Aberystwyth. Sponsorship: JISC

Training for professional librarians in Slovakia by distance-learning methods: an overview of the PROLIB and EDULIB projects

Tedd, L.A., Dahl, K., Francis, S.,Tet?evov?, M.& ?ihlavn?kov?, E.(2002).Training for professional librarians in Slovakia by distance-learning methods: an overview of the PROLIB and EDULIB projects. Library Hi Tech, 20(3), 340-351. Sponsorship: European Union and the Open Society Institute

Developmental Learning for Autonomous Robots

M.H. Lee, Q. Meng and F. Chao, 'Developmental Learning for Autonomous Robots', Robotics and Autonomous Systems, 55(9), pp 750-759, 2007.

Psychologically Inspired Sensory-Motor Development in Early Robot Learning

Lee, M., Meng, Q. (2005). Psychologically Inspired Sensory-Motor Development in Early Robot Learning. International Journal of Advanced Robotic Systems, 325-334.

Learning from triads: training undergraduates in counselling skills

Background: Research has shown that counselling skills training in undergraduate programmes is effective. However, there is potential that premature intimacy and disclosures during triad work may impact on relationships which must be maintained out-with the counselling component of the course. Little research has examined individual pedagogical practices within training. Aim: The aim of this research was to explore the experience of the practical skills training component of a counselling course for a cohort of undergraduate students, and the impact of this learning experience. The objective being an evaluation of the use of this approach for this group and of the impact of personal sharing within cohorts of undergraduates. Method: Semi-structured interviews focusing on the experience of skills training and self-disclosure during training were carried out on 12 undergraduates taking counselling skills modules as part of their BSc Psychology and Counselling degree. Thematic analysis was carried out on the interview transcripts. Results: As a result of engagement in skills training and acting as ‘clients’ for one another, individuals perceived the formation of a positive group identity with implicit ‘rules’, but also an impact of training on relationships within the group which relied on the ability to maintain boundaries and personal identities with peers, and this influenced the learning experience. The ability to manage their engagement on the programme was dependent on ongoing support and guidance from tutors. Discussion: While this pedagogical approach appears appropriate for facilitating learning and potentially provides a rich learning journey for undergraduate students, tutors must act proactively to ensure a safe learning environment.

Zintegrowane kształcenie przedmiotowo-językowe. Dydaktyka zadaniowa a rozwój osobistej kompetencji komunikacyjnej w warunkach półautonomii

Wydział Neofilologii

Teaching Crossroads: 11th IPB Erasmus Week

In the wake of the latest news regarding IPB’s award for best Polytechnic Institute in Portugal, we would like to congratulate the IPB community who has always striven for the quality of the institution within the national and international academic milieu. We are, undoubtedly, bowled over by the 1st place in the national context (out of the 27 national institutions under evaluation) and the 7th position in the international scope. In fact, it is worth mentioning that the IPB has won this award, three years in a row, being in a leading position in the ranking promoted and sponsored by the European Union. This year’s edition has selected and evaluated over 1300 world higher education institutions. Teaching Crossroads intends thus to give a watershed contribution to the IPB’s successful and most valued pathway. Numbers indicate that Teaching Crossroads has had over 2550 downloads since it first came out. But let’s cut to the chase. Once again, we are delighted to present the 5th number of Teaching Crossroads. This wholly calculated and well-sustained editorial adventure started in 2012 when the first number of Teaching Crossroads first saw the light. This year’s publication includes the areas of Human Geography/anthropology, Information Technology and Forensics and Language and culture, focusing on minority languages. Alongside this, as in the two last previous numbers, we’ve included the specific area for International mobility, Intensive Programmes and Erasmus+ Mobility of Individuals, being the latter financed by the European Union within the Erasmus+ Programme, whereas the former is sponsored uniquely by the foreign partner institution, in this case, Lillebaelt Academy in Denmark. These types of programmes convey very positive and overarching ideas, resonant in cross-cultural and educational benefits, valuable for all the involved partners. We would very kindheartedly like to thank the authors for having contributed with much enlightening and serious articles on a wide array of areas. Pablo M. Orduna Pórtus’s article focuses on border culture and heritage management. The author’s study is placed on two borderlands of the Iberian Peninsula: Roncal Valley (Navarre) and Riverbanks of Douro. Going beyond the linear or physical conception of the border, the author centres his study on the metaphysical and symbolic ideas of the frontier that sustain his anthropological analysis. Michal Popdora manages to find evidence for his proposal of a new conception of teaching Image Processing, based on the student-centered approach. A hands-on experience on a Project-based Learning methodology sustains the teaching project. Grounded on “a forensic-flavored style”, using the author’s own words, he shows how students can become engaged in a highly effective learning process. Cláudia Martins is already a confirmed habitué of this publication, as in every Erasmus Week she delivers a lecture on Portuguese language and culture to visiting teaching and non-teaching staff. This time, the author decided to delve into a Portugal’s official language, Mirandese, spoken in a small designated area in the northeastern part of Portugal, Miranda do Douro and its surrounding area. The author gives account of some thought-provoking facts about the language, from the origin and the survival of the language, however still a minority language, up to the moment when it was acknowledged Portugal’s second official language, together with the challenges that nowadays faces. Luís Frölen Ribeiro, João Eduardo Ribeiro, Carlos Casimiro Costa, António Duarte, Carlos Andrade from the Polytechnic Institute and Arne Svinth, John Madsen, Morten Thomsen, Kent Smidstrup, Carsten John Jacobsen from the Lillebaelt Academy, in Denmark, participate in a joint project which they describe, outlining the main goals and gains of the project. To overcome teaching difficulties regarding the engineering degrees, a 12-ECTS joint course from Lillebaelt Academy and Polytechnic Institute of Bragança was created based on the Danish model. The course Product Development and Industrial Processing was hence created. Rui Pedro Lopes presents an insightful and acute account of the Internationalization programmes in Higher Education in Europe. At one go, the author describes his own experience as a visiting lecturer, within the Erasmus+ programme, to Università Politecnica delle Marche in Ancona, Italy, in a Master’s degree in computer science, bringing to light a personal reflection on the goals and benefits of the mobility for both students and teachers. Finally, the author puts forth some suggestions that would improve the whole mobility process. We sincerely hope to have stimulated you to keep on reading, upholding the belief that these texts can represent valuable sources for both teachers and students in their research work.

The DSpace Course - Item Submission Workflows

This module will introduce the item submission workflows available in DSpace. Workflows allow submissions to be checked before entering the repository. Submissions may be checked for accuracy, in order to improve the metadata, or simply to decide if they are OK to be archived. The module will show the three workflow steps available in DSpace, along with details about adding, changing and removing them from the submission process of collections.

Simultaneous Learning of Nonlinear Manifold and Dynamical Models for High-dimensional Time Series

The goal of this work is to learn a parsimonious and informative representation for high-dimensional time series. Conceptually, this comprises two distinct yet tightly coupled tasks: learning a low-dimensional manifold and modeling the dynamical process. These two tasks have a complementary relationship as the temporal constraints provide valuable neighborhood information for dimensionality reduction and conversely, the low-dimensional space allows dynamics to be learnt efficiently. Solving these two tasks simultaneously allows important information to be exchanged mutually. If nonlinear models are required to capture the rich complexity of time series, then the learning problem becomes harder as the nonlinearities in both tasks are coupled. The proposed solution approximates the nonlinear manifold and dynamics using piecewise linear models. The interactions among the linear models are captured in a graphical model. By exploiting the model structure, efficient inference and learning algorithms are obtained without oversimplifying the model of the underlying dynamical process. Evaluation of the proposed framework with competing approaches is conducted in three sets of experiments: dimensionality reduction and reconstruction using synthetic time series, video synthesis using a dynamic texture database, and human motion synthesis, classification and tracking on a benchmark data set. In all experiments, the proposed approach provides superior performance.

Simultaneous Learning of Non-Linear Manifold and Dynamical Models for High-Dimensional Time Series

The goal of this work is to learn a parsimonious and informative representation for high-dimensional time series. Conceptually, this comprises two distinct yet tightly coupled tasks: learning a low-dimensional manifold and modeling the dynamical process. These two tasks have a complementary relationship as the temporal constraints provide valuable neighborhood information for dimensionality reduction and conversely, the low-dimensional space allows dynamics to be learnt efficiently. Solving these two tasks simultaneously allows important information to be exchanged mutually. If nonlinear models are required to capture the rich complexity of time series, then the learning problem becomes harder as the nonlinearities in both tasks are coupled. The proposed solution approximates the nonlinear manifold and dynamics using piecewise linear models. The interactions among the linear models are captured in a graphical model. The model structure setup and parameter learning are done using a variational Bayesian approach, which enables automatic Bayesian model structure selection, hence solving the problem of over-fitting. By exploiting the model structure, efficient inference and learning algorithms are obtained without oversimplifying the model of the underlying dynamical process. Evaluation of the proposed framework with competing approaches is conducted in three sets of experiments: dimensionality reduction and reconstruction using synthetic time series, video synthesis using a dynamic texture database, and human motion synthesis, classification and tracking on a benchmark data set. In all experiments, the proposed approach provides superior performance.

A Model of Cerebellar Adaptation of Grip Forces During Lifting

We investigated adaptive neural control of precision grip forces during object lifting. A model is presented that adjusts reactive and anticipatory grip forces to a level just above that needed to stabilize lifted objects in the hand. The model obeys priciples of cerebellar structure and function by using slip sensations as error signals to adapt phasic motor commands to tonic force generators associated with output synergies controlling grip aperture. The learned phasic commands are weight and texture-dependent. Simulations of the new curcuit model reproduce key aspects of experimental observations of force application. Over learning trials, the onset of grip force buildup comes to lead the load force buildup, and the rate-of-rise of grip force, but not load force, scales inversely with the friction of the gripped object.

AIRSTREAM: A Neural Network Model of Auditory Scene Analysis and Source Segregation

Multiple sound sources often contain harmonics that overlap and may be degraded by environmental noise. The auditory system is capable of teasing apart these sources into distinct mental objects, or streams. Such an "auditory scene analysis" enables the brain to solve the cocktail party problem. A neural network model of auditory scene analysis, called the AIRSTREAM model, is presented to propose how the brain accomplishes this feat. The model clarifies how the frequency components that correspond to a give acoustic source may be coherently grouped together into distinct streams based on pitch and spatial cues. The model also clarifies how multiple streams may be distinguishes and seperated by the brain. Streams are formed as spectral-pitch resonances that emerge through feedback interactions between frequency-specific spectral representaion of a sound source and its pitch. First, the model transforms a sound into a spatial pattern of frequency-specific activation across a spectral stream layer. The sound has multiple parallel representations at this layer. A sound's spectral representation activates a bottom-up filter that is sensitive to harmonics of the sound's pitch. The filter activates a pitch category which, in turn, activate a top-down expectation that allows one voice or instrument to be tracked through a noisy multiple source environment. Spectral components are suppressed if they do not match harmonics of the top-down expectation that is read-out by the selected pitch, thereby allowing another stream to capture these components, as in the "old-plus-new-heuristic" of Bregman. Multiple simultaneously occuring spectral-pitch resonances can hereby emerge. These resonance and matching mechanisms are specialized versions of Adaptive Resonance Theory, or ART, which clarifies how pitch representations can self-organize durin learning of harmonic bottom-up filters and top-down expectations. The model also clarifies how spatial location cues can help to disambiguate two sources with similar spectral cures. Data are simulated from psychophysical grouping experiments, such as how a tone sweeping upwards in frequency creates a bounce percept by grouping with a downward sweeping tone due to proximity in frequency, even if noise replaces the tones at their interection point. Illusory auditory percepts are also simulated, such as the auditory continuity illusion of a tone continuing through a noise burst even if the tone is not present during the noise, and the scale illusion of Deutsch whereby downward and upward scales presented alternately to the two ears are regrouped based on frequency proximity, leading to a bounce percept. Since related sorts of resonances have been used to quantitatively simulate psychophysical data about speech perception, the model strengthens the hypothesis the ART-like mechanisms are used at multiple levels of the auditory system. Proposals for developing the model to explain more complex streaming data are also provided.