his.sePublications
Change search
Refine search result
1 - 8 of 8
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the 'Create feeds' function.
  • 1.
    Duran, Boris
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Sandamirskaya, Yulia
    Institute of Neuroinformatics, University and ETH Zurich, Zurich, Switzerland.
    Learning Temporal Intervals in Neural Dynamics2017In: IEEE Transactions on Cognitive and Developmental Systems, ISSN 2379-8920Article in journal (Refereed)
  • 2.
    Durán, Boris
    et al.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Lee, Gauss
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Lowe, Robert
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Learning a DFT-based sequence with reinforcement learning: A NAO implementation2012In: Paladyn - Journal of Behavioral Robotics, ISSN 2080-9778, E-ISSN 2081-4836, Vol. 3, no 4, p. 181-187Article in journal (Refereed)
  • 3.
    Durán, Boris
    et al.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Sandamirskaya, Yulia
    Ruhr-Universität Bochum, Institut für Neuroinformatik, Universitätstr. 150, 44780 Bochum, Germany.
    Schöner, Gregor
    Ruhr-Universität Bochum, Institut für Neuroinformatik, Universitätstr. 150, 44780 Bochum, Germany.
    A dynamic field architecture for the generation of hierarchically organized sequences2012In: Artificial Neural Networks and Machine Learning – ICANN 2012: 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, September 11-14, 2012, Proceedings, Part I / [ed] Alessandro E. P. Villa, Włodzisław Duch, Péter Érdi, Francesco Masulli, Günther Palm, Springer Berlin/Heidelberg, 2012, no PART 1, p. 25-32Conference paper (Refereed)
    Abstract [en]

    A dilemma arises when sequence generation is implemented on embodied autonomous agents. While achieving an individual action goal, the agent must be in a stable state to link to fluctuating and time-varying sensory inputs. To transition to the next goal, the previous state must be released from stability. A previous proposal of a neural dynamics solved this dilemma by inducing an instability when a "condition of satisfaction" signals that an action goal has been reached. The required structure of dynamic coupling limited the complexity and flexibility of sequence generation, however. We address this limitation by showing how the neural dynamics can be generalized to generate hierarchically structured behaviors. Directed couplings downward in the hierarchy initiate chunks of actions, directed couplings upward in the hierarchy signal their termination. We analyze the mathematical mechanisms and demonstrate the flexibility of the scheme in simulation. © 2012 Springer-Verlag.

  • 4.
    Durán, Boris
    et al.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Thill, Serge
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Modelling interaction in multi-modal affordance processing with neural dynamics2012In: From Animals to Animats 12: 12th International Conference on Simulation of Adaptive Behavior, SAB 2012, Odense, Denmark, August 27-30, 2012. Proceedings / [ed] Tom Ziemke, Christian Balkenius, John Hallam, Berlin, Heidelberg: Springer Berlin/Heidelberg, 2012, p. 75-84Conference paper (Refereed)
    Abstract [en]

    Behavioral studies on the activation of affordances by understanding observation and action sentences on graspable objects show a direct relationship between the canonical orientation of graspable objects, their dimension and the kind of grip required by those objects to be grasped. The present work introduces the concepts of Dynamic Field Theory for modeling the results observed in the behavioral studies previously mentioned. The model was not only able to replicate qualitatively similar results regarding reaction times, but also the identification of same versus different object and the distinction between observable versus action sentences. The model shows the potential of dynamic field theory for the design and implementation of brain inspired cognitive systems. © 2012 Springer-Verlag.

  • 5.
    Li, Cai
    et al.
    University of Skövde, School of Humanities and Informatics.
    Lowe, Robert
    University of Skövde, School of Humanities and Informatics.
    Duran, Boris
    University of Skövde, School of Humanities and Informatics.
    Ziemke, Tom
    University of Skövde, School of Humanities and Informatics.
    Humanoids that crawl: Comparing gait performance of iCub and NAO using a CPG architecture2011In: Proceedings - 2011 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2011 / [ed] Shaozi Li, Ying Dai, IEEE conference proceedings, 2011, p. 577-582Conference paper (Refereed)
    Abstract [en]

    In this article, a generic CPG architecture is used to model infant crawling gaits and is implemented on the NAO robot platform. The CPG architecture is chosen via a systematic approach to designing CPG networks on the basis of group theory and dynamic systems theory. The NAO robot performance is compared to the iCub robot which has a different anatomical structure. Finally, the comparison of performance and NAO whole-body stability are assessed to show the adaptive property of the CPG architecture and the extent of its ability to transfer to different robot morphologies. © 2011 IEEE.

  • 6.
    Lowe, Robert
    et al.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Duran, Boris
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Ziemke, Tom
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    A Dynamic Field Theoretic Model of Iowa Gambling Task Performance2010In: 2010 IEEE 9th International Conference on Development and Learning (ICDL): Ann Arbor, MI, August 18-21, 2010, IEEE conference proceedings, 2010, p. 297-304Conference paper (Refereed)
    Abstract [en]

    Choice behaviour where outcome-contingencies vary or are prohabilistic has been the focus of many benchmark tasks of infant to adult development in the psychology literature. Dynamic field theoretic (DFT) investigations of cognitive and behavioural competencies have been used in order to identify parameters critical to infant development. In this paper we report the findings of a DFT model that is able to replicate normal functioning adult  performance on the Iowa gambling task (IGT).  The model offers a simple demonstration proof of the parsimonious reversal learning alternative to Damasio’s somatic marker  explanation of IGT performance. Our simple model demonstrates a potentially important role for reinforcement/reward learning to generating behaviour that allows for advantageous performance. We compare our DFT modelling approach to one used on the A-not-B infant paradigm and suggest that a critical aspect of development lies in the ability to flexibly trade off perseverative versus exploratory behaviour in order to capture statistical choice-outcome contingencies. Finally, we discuss the importance of an investigation of the IGT in an embodied setting where reward prediction learning may provide critical means by which adaptive behavioural reversals can be enacted.

  • 7.
    Thill, Serge
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Duran, BorisUniversity of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.Hemeren, PaulUniversity of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Social signals in action recognition and intention understanding2013Collection (editor) (Refereed)
  • 8.
    Thill, Serge
    et al.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Hemeren, Paul E.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Durán, Boris
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Prediction of human action segmentation based on end-effector kinematics using linear models2011In: European Perspectives on Cognitive Science: Proceedings of the European Conference on Cognitive Science / [ed] Kokinov, B. et al., Sofia: New Bulgarian University Press , 2011, p. 6 sidor-Conference paper (Refereed)
    Abstract [en]

    The work presented in this paper builds on previous research which analysed human action segmentation in the case of simple object manipulations with the hand (rather than larger-scale actions). When designing algorithms to segment observed actions, for instance to train robots by imitation, the typical approach involves non-linear models but it is less clear whether human action segmentation is also based on such analyses. In the present paper, we therefore explore (1) whether linear models built from observed kinematic variables of a human hand can accurately predict human action segmentation and (2) what kinematic variables are the most important in such a task. In previous work, we recorded speed, acceleration and change in direction for the wrist and the tip of each of the five fingers during the execution of actions as well as the segmentation of these actions into individual components by humans. Here, we use this data to train a large number of models based on every possible training set available and find that, amongst others, the speed of the wrist as well as the change in direction of the index finger were preferred in models with good performance. Overall, the best models achieved R2 values over 0.5 on novel test data but the average performance of trained models was modest. We suggest that this is due to a suboptimal training set (which was not specifically designed for the present task) and that further work be carried out to identify better training sets as our initial results indicate that linear models may indeed be a viable approach to predicting human action segmentation.

1 - 8 of 8
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf