Emilia I. Barakova

Emilia I. Barakova , Ph.D. Faculty of Industrial Design, Eindhoven University of Technology Den Dolech 2 5612 AZ Eindhoven The Netherlands

formerly  

Lab. for Dynamics of Emergent Intelligence, RIKEN Brain Science Institute (BSI), 2-1, Hirosawa, Wako-shi, Saitama, 351-0198 Japan

Wikitherapist: robots for autism

Robot interacting socially with a child

Wikitherapist and ZonMW projects on Robots for Social training of children with ASD. The Wikitherapist project aims to empower health researchers/practitioners with robot assistants or mediators in behavioral therapies for children with autism. This process combines (a) a user centered design of a platform to support therapists to create and share behavioral training scenarios with robots and (b) acquisition of domain specific knowledge from the therapists in order to design robot-child interaction scenarios that accomplish specific learning goals for the autistic children. Wikitherapist - Robotics for autistic care

AMHA

ESA prepares for a human mission to Mars (credits: ESA)

The AMHA (Automatic Mental Health Assistant) project is part of the Mars-500 experiment carried out at the Institute for Biomedical Problems (IBMP) in Moscow in collaboration with the European Space Agency (ESA) and the Russian Academy of Sciences who jointly conduct an experiment in order to simulate a manned mission to Mars. The isolated space environment during ultra long flights affects a number of psychosocial and mental processes critically involved in human performance. In this project, we explore the use of collaborative multi-player games as an unintrusive tool to monitor the development of different social interaction patterns within the crew. Automatic Mental Health Assistant

Neurorobotics

Grasping by sensory delay

We use a combination of methods consisting of functional brain modeling, behavioral robotics, and human centered design for designing social behaviors for robots and robotic toys. Modelling grasping behavior of autistic and typical children and making a game on the basis of it is one example for this research.

    1. Publications

        Recent papers

      1. Barakova, E.I., M. de Haas, Kuijpers, W.J.P., Irigoyen Perdiguero, N., Betancourt, A., Socially Grounded Game Strategy Enhances Bonding and Perceived Smartness of a Humanoid Robot, Connection Science, in press [pdf- ask for a copy]

      2. JS Olier, E Barakova, C Regazzoni, M Rauterberg, Re-framing the characteristics of concepts and their relation to learning and cognition in artificial agents Cognitive Systems Research 44, 50-68, 2017. [pdf]

      3. Alejandro Betancourt, Pietro Morerio, Emilia Barakova, Lucio Marcenaro, Matthias Rauterberg, Carlo Regazzoni Left/right hand segmentation in egocentric videos Computer Vision and Image Understanding , 154, 73-81. (2017). [pdf]

      4. Effects of robots' intonation and bodily appearance on robot-mediated communicative treatment outcomes for children with autism spectrum disorder Effects of robots' intonation and bodily appearance on robot-mediated communicative treatment outcomes for children with autism spectrum disorder, Personal and Ubiquitous Computing, in press, 2017. % [pdf- ask for a copy]

      5. Robots for Behavioral Training of Children with Autism

      6. Emilia I. Barakova, Prina Bajracharya, Marije Willemsen, Tino Lourens and Bibi Huskens, Long-term LEGO therapy with humanoid robot for children with ASD, Expert Systems Volume 32, Issue 6, pages 698–709, December 2015. [pdf]

      7. Bibi Huskens, Annemiek Palmen, Marije Van der Werff, Tino Lourens, Emilia Barakova Improving Collaborative Play Between Children with Autism Spectrum Disorders and Their Siblings: The Effectiveness of a Robot-Mediated Intervention Based on Lego Therapy, Journal of Autism and Developmental Disorders, 45(11), 3746-3755. doi:10.1007/s10803-014-2326-0 [pdf]

      8. Huskens, B., Verschuur, R., Gillesen, J., Didden, R., and Barakova, E., Promoting question-asking in school-aged children with autism spectrum disorders: Effectiveness of a robot intervention compared to a human-trainer intervention. Journal of Developmental Neurorehabilitation, 16(5): 345–356, October 2013; [pdf]

      9. E.I. Barakova, J.C.C. Gillesen, B.E.B.M. Huskens, T. Lourens, End-user programming architecture facilitates the uptake of robots in social therapies Robotics and Autonomous Systems, 61, 704–713. (2013). [pdf]

      10. Michael A. Goodrich, Jacob W. Crandall, & Emilia Barakova Teleoperation and Beyond for Assistive Humanoid Robots, Reviews of Human Factors and Ergonomics, vol9(1), , pp. 175-226, 2013. [pdf]

      11. Min-Gyu Kim, Emilia I. Barakova, Tino Lourens Rapid Prototyping Framework for Robot-assisted Training of Autistic Children, RO-MAN 2014, pp 1101-1106. %[pdf]

      12. Alberto Gruarin, Michel A. Westenberg, and Emilia I. Barakova, StepByStep: Design of an Interactive Pictorial Activity Game for Teaching Generalization Skills to Children with Autism, LNCS 8215,, pp. 87–92, 2013 [pdf]

      13. Costanza Giuffrida and Emilia I. Barakova , Time processing ability and anxiety in children with autism: evaluation of the effects of music using music timer PLAYtime. , IASDR 2013, Aug.26-30, Tokyo, Japan [pdf]

      14. J.C.C. Gillesen, E.I. Barakova, B.E.B.M. Huskens, L.M.G. Feijs, From training to robot behavior: Towards custom scenarios for robotics in training programs for ASD 2011 IEEE International Conference on Rehabilitation Robotics , pp. 387 - 393, Rehab Week Zurich, ETH Zurich Science City, Switzerland, June 29 - July 1, 2011 [pdf]

      15. E.I. Barakova, T. Lourens, Interplay between Natural and Artificial Intelligence in Training Autistic Children with Robots, LNCS 7930, pp. 161–170, 2013 [pdf]

      16. E.I. Barakova, Robots for social training of autistic children Empowering the therapists in intensive training programs In Abraham et al. eds., Proceedings of IEEE WICT 2011, pp. 14- 19, 2011 A. [pdf]

      17. M. Dimitrova, N. Vegt, and E. Barakova, "Designing a system of interactive robots for training collaborative skills to autistic children" in Interactive Collaborative Learning (ICL), 2012 15th International Conference on, 2012, pp. 1-8. [pdf]

      18. E. I. Barakova, J. Gillessen, and L. Feijs Social training of autistic children with interactive intelligent agents Journal of Integrative Neuroscience, 8(1):23-34, 2009. [pdf]

      19. Emilia I. Barakova and Winai Chonnaparamutt Timing sensory integration for robot simulation of autistic behavior IEEE Robotics and Automation Magazine , 16(3):51-58, 2009. [pdf]

      20. Emilia I. Barakova and Loe Feijs Brain-inspired robots for autistic training and care in J. Krichmar and H. Wagatsuma (Eds.), Neuromorphic and Brain-Based Robots: Trends and Perspectives, Cambridge University Press, pp. 178-214, Edinburgh, Augist 2011. [pdf]

      21. Emilia I. Barakova and Tino Lourens Expressing and interpreting emotional movements in social games with robots Personal and Ubiquitous Computing, 14:457–467, 2010. [pdf]

      22. J. C. J. Brok, E. I. Barakova Engaging autistic children in imitation and turn-taking games with multiagent system of interactive lighting blocks >in H.S. Yang et al. (Eds.): ICEC 2010, ., LNCS 6243, pp. 115–126, 2010. [pdf]

      23. S. H. M. Alers, E. I. Barakova Multi-agent platform for development of educational games for children with autism [625 KB pdf].IEEE ICE CIG 2009, pp 47-53, ISBN: 978-1-4244-4459-5, 2009 .
      24. T. Lourens and E. I. Barakova User-Friendly Robot Environment for Creation of Social Scenarios. in Foundations on Natural and Artificial Computation. J. Ferrández, et al., Eds.,: , LNCS 6686, pp. 212-221, 2011
      25. E. I. Barakova, G. van Wanrooij, R. van Limpt, and M. Menting Using an emergent system concept in designing interactive games for autistic children [401 KB pdf]. 6th International Conference on Interaction Desing and Children (IDC07), pages 73-77, Aalborg Denmark, June 2007. ACM 978-1-59593-747-6.

      26. D. Tetteroo, A. Shirzad, M. Serras Pereira, M. Zwinderman, D. Le, E. Barakova Mimicking Expressiveness Of Movements By Autistic Children In Game Play. In: in International Confernece on Social Computing (SocialCom), 2012, pp. 944-949. [pdf]

      27. Social robots, emotions in movement behavior, measuring behavior

      28. Mirza Waqar Baig, Emilia I. Barakova, Lucio Marcenaro, Carlo S. Regazzoni, Matthias Rauterberg, Bio-Inspired Probabilistic Model for Crowd Emotion Detection. International Joint Conference on Neural Networks (IJCNN 2014), within the 2014 IEEE World Congress on Computational Intelligence (WCCI 2014), 6-11 July 2014 - Beijing, China; [pdf]

      29. Tino Lourens, Roos van Berkel, and Emilia Barakova Communicating emotions and mental states to robots in a real time parallel framework using Laban movement analysis. Robotics and Autonomous Systems, 58 pp. 1256–1265, 2010.

      30. Emilia I. Barakova and Tino Lourens Expressing and interpreting emotional movements in social games with robots. Personal and Ubiquitous Computing, (2010) 14:457–467.
      31. Emilia I. Barakova, Andrew S. Spink, Boris de Ruyter and Lucas P. J. J. Noldus Trends in measuring human behavior and interaction Personal and Ubiquitous Computing 1-2. Springer, doi: 10.1007/s00779-011-0478-x [pdf]

      32. Mirza Waqar Baig, Emilia I. Barakova, Lucio Marcenaro, Matthias Rauterberg, Carlo S. Regazzoni, Crowd Emotion Detection Using Dynamic Probabilistic Models. The Simulation of Adaptive Behavior (SAB), 13th International Conference on - Castellon, Spain, 22-26 July 2014; [pdf]

      33. Liang Hiah, Luuk Beursgens, Roy Haex, Lilia Perez Romero, Yu-Fang Teh, Martijn ten Bhömer, Roos van Berkel, and E. I. Barakova Abstract Robots with an Attitude: Applying Interpersonal Relation Models to Human-Robot Interaction, Proceedings of IEEE RO-MAN: The 22nd IEEE International Symposium on Robot and Human Interactive Communication, Gyeongju, Korea, August 26-29, 2013. [pdf]

      34. Emilia I. Barakova, Andrew S. Spink, Naotaka Fujii From neuron to behavior: evidence from behavioral measurements Neurocomputing, vol. 84, pp. 1-2, 2012 Elsevier B.V. [pdf]

      35. T. Lourens and E. I. Barakova. Retrieving Emotion from Motion Analysis: In a Real Time Parallel Framework for Robots. In C.S. Leung, M. Lee, and J.H. Chan (Eds.): ICONIP 2009,, Part II, LNCS 5864, pp. 430–438, 2009.
      36. T. Lourens and E. I. Barakova. My Sparring Partner is a Humanoid Robot -A parallel framework for improving social skills by imitation [1646 KB pdf]. In J. R. Alvarez, editor, IWINAC 2009, number 5602 in Lecture Notes in Computer Science, pages 344-352, Santiago de Compostella, Spain, June 2009. Springer-verlag.
      37. E. I. Barakova and D. Vanderelst From Spreading of Behavior to Dyadic Interaction—A Robot Learns What to Imitate. International Journal of Intelligent Systems, VOL. 26, 228–245 (2011) .DOI 10.1002/int.20464
      38. Dieter Vanderelst , Rene M.C. Ahn, Emilia I. Barakova Simulated Trust: A cheap social learning strategy[330 KB pdf]. Theoretical Population Biology, Volume 76, Issue 3, Pages 189-196 November 2009.
      39. E. I. Barakova and T. Lourens. Mirror neuron framework yields representations for robot interaction [858 KB pdf]. Neurocomputing, 72(4-6):895-900, 2009.
      40. Martijn ten Bhömer, Kirstin van der Aalst, Emilia Barakova and Philip Ross. Product adaptivity through movement analysis: the case of the intelligent walk-in closet. In DeSForM 2009 , October 26, 2009 – October 27, 2009. [pdf]

      41. Games and Modelling social behavior

      42. Gorbunov, R., Barakova, E., Rauterberg, G.W.M. Design of social agents, Neurocomputingvol. 114, pp. 92-97, 2013. [pdf]

      43. Gorbunov, R., Barakova, E., Ahn, R., Rauterberg, G.W.M. Monitoring Interpersonal Relationships through Games with Social Dilemma Proceedings of International Conference on Evolutionary Computation Theory and Applications pp. 5-12, Paris, France, October 2011. ----BEST PAPER AWARD------ [pdf]

      44. Gorbunov, R., Barakova, E., Ahn, R., Rauterberg, G.W.M. Adaptive Properties and Memory of a System of Interactive Agents: A Game Theoretic Approach The Fourth International Conference on Adaptive and Self-Adaptive Systems and Applications , pp: 103 - 108, Nice, France 22 to 27 July, 2012, ISBN 978-1-61208-219-6. [pdf]

      45. Willemsen W., Mestrom R., and Barakova E., The Application of Learning Algorithms in the Development of Natural Interaction Proceedings of DSSIRE'11 - Creativity and Innovation Design pp. 81-84, Eindhoven, The Netherlands, October 2011. ----BEST PAPER NOMINATION------ [pdf]

      46. Voynarovskaya, N., Gorbunov, R., Barakova, E., Ahn, R., Rauterberg, G.W.M. Nonverbal Behavior Observation: Collaborative Gaming Method for Prediction of Conflicts during Long-term Missions. In H.S. Yang et al. (Eds.): ICEC 2010, LNCS 6243, pp. 103-114, 2010. [pdf]

      47. Voynarovskaya, N., Gorbunov, R., Barakova, E., Rauterberg, G.W.M. Automatic Mental Heath Assistant: Monitoring and Measuring Nonverbal Behavior of the Crew During Long-Term Missions. Extended abstracts in ACM Proceedings of 7th International Conference on Methods and Techniques in Behavioral Research. Eindhoven, the Netherlands, 2010. [pdf]

      48. Tilde Bekker, Janienke Sturm, Emilia Barakova Design for social interaction through physical play in diverse contexts of use Personal and Ubiquitous Computing , Vol. 14, No. 5, p.381-383, 2010. [pdf]

      49. Emilia I. Barakova and Tino Lourens Expressing and interpreting emotional movements in social games with robots Personal and Ubiquitous Computing, 14:457–467, 2010. [pdf]

      50. Neurorobotics

      51. Emilia I. Barakova and Winai Chonnaparamutt Timing sensory integration for robot simulation of autistic behavior [336 KB pdf]. IEEE Robotics and Automation Magazine , 16(3):51-58, 2009.
      52. T. Lourens, E. I. Barakova, H. G. Okuno, and H. Tsujino. A computational model of monkey cortical grating cells [478 KB pdf]. Biological Cybernetics, 92(1):61-70, January 2005. DOI: 10.1007/s00422-004-0522-2.

      53. E. I. Barakova and T. Lourens. Event based self-suprevised temporal integration for multimodal sensor data. [702 KB pdf]. Journal of Integrative Neuroscience, 4(2):265-282, June 2005. DOI: 10.1142/S021963520500077X.

      54. E. I. Barakova and T. Lourens. Mirror neuron framework yields representations for robot interaction [858 KB pdf]. Neurocomputing, 72(4-6):895-900, 2009.
      55. T. Lourens and E. I. Barakova. Orientation Contrast Sensitive Cells in Primate V1 -a computational model [607 KB pdf]. Natural Computing, 6(3):241-252, September 2007.

      56. E. I. Barakova and T. Lourens. Efficient episode encoding for spatial navigation. International Journal of Systems Science, 36:14, 887-895, 2005. http://dx.doi.org/10.1080/00207720500382209

      57. E. I. Barakova, T. Lourens, and Y. Yamaguchi. Life-long learning: consolidation of novel events into dynamic memory representations [327 KB pdf]. In J. Mira and J. R. Alvarez, editors, Proceedings of the International Work-Conference on Artificial and Natural Neural Networks, IWANN 2003, volume 2686 of Lecture Notes in Computer Science, pages 110-117, Menorca, Spain, June 2003. Springer-Verlag.

      58. E. I. Barakova and T. Lourens. Event based self-suprevised temporal integration for multimodal sensor data. [702 KB pdf]. Journal of Integrative Neuroscience, 4(2):265-282, June 2005. DOI: 10.1142/S021963520500077X.

      59. E. I. Barakova and T. Lourens. Spatial navigation based on novelty mediated autobiographical memory [364 KB pdf]. In J. Mira and J. R. Alvarez, editors, IWINAC 2005, number 3561 in Lecture Notes in Computer Science, pages 1-10, Las Palmas de Gran Canaria, Spain, June 2005. Springer-verlag.

      60. T. Lourens and E. I. Barakova. Simulation of Orientation Contrast Sensitive Cell Behavior in TiViPE [455 KB pdf]. In J. Mira and J. R. Alvarez, editors, IWINAC 2005, number 3561 in Lecture Notes in Computer Science, pages 57-66, Las Palmas de Gran Canaria, Spain, June 2005. Springer-verlag.

      61. T. Lourens and E. I. Barakova. TiViPE Simulation of a Cortical Crossing Cell Model. [1786 KB pdf]. In J. Cabastany, A. Prieto, and D. F. Sandoval, editors, IWANN 2005, number 3512 in Lecture Notes in Computer Science, pages 122-129, Barcelona, Spain, June 2005. Springer-verlag.

      62. Maya Dimitrova, Emilia Barakova, Tino Lourens, and Petia Radeva. The web as an autobiographical agent [597 KB pdf]. In C. Bussler and D. Fensel, editors, Artificial Intelligence: Methodology, Systems, and Applications, 11th International Conference, AIMSA 2004, volume 3192 of Lecture Notes in Artificial Intelligence, pages 510-519. Springer-Verlag, 2004.

      63. E. I. Barakova Familiarity Gated Learning for Inferential use of Episodic Memories in Novel Situations - A robot simulation [638 KB pdf]. In L. S. Smith, A. Hussain and I. Aleksander, editors, Brain Inspired Cognitive Systems 2004, pages 1-7 (BIS 1-5). Department of Computing Science and Mathematics, University of Stirling, Stirling FK9 4LA, Scotland, UK, 2004, ISBN 1 85769 199 7.

      64. E. I. Barakova Emergent behaviors based on episodic encoding and familiarity driven retrieval [431 KB pdf]. In C. Bussler and D. Fensel, editors, Artificial Intelligence: Methodology, Systems, and Applications, 11th International Conference, AIMSA 2004, volume 3192 of Lecture Notes in Artificial Intelligence, pages 188-197. Springer-Verlag, 2004.

      65. E. I. Barakova and T. Lourens. Novelty gated episodic memory formation for robot exploration [1166 KB pdf]. In R. R. Yager and V. S. Sgurev, editors, Second International IEEE Conference on Intelligent Systems (IS 2004), volume I, pages 116-121, Varna, Bulgaria, June 2004.

      66. T. Lourens, E. I. Barakova, and H. Tsujino. Interacting Modalities through Functional Brain Modeling [225 KB pdf]. In J. Mira and J. R. Alvarez, editors, Proceedings of the International Work-Conference on Artificial and Natural Neural Networks, IWANN 2003, volume 2686 of Lecture Notes in Computer Science, pages 102-109, Menorca, Spain, June 2003. Springer-Verlag.

      67. E. I. Barakova and T. Lourens. Prediction of Rapidly Changing Environmental Dynamics for Real Time Behavior Adaptation using Visual Information [134 KB pdf]. In R. P. Wurtz and M. Lappe, editors, 4th Workshop on Dynamic Perception, pages 147-152, Bochum, Germany, November 2002. IOS press.

      68. T. Lourens and E. I. Barakova. Real Time Object Recognition in a Dynamic Environment -An application for soccer playing robots [1203 KB pdf]. In R. P. Wurtz and M. Lappe, editors, 4th Workshop on Dynamic Perception, pages 189-194, Bochum, Germany, November 2002. IOS press.

      69. E. I. Barakova An Integration Principle for Multimodal Sensor Data Based on Temporal Coherence of Self-Organized Patterns [104 KB pdf]. In J. Mira R. Moreno-Diaz, and J. Cabestany, editors, Biological and Artificial Computation: Methodologies, Neural Modeling and Bioengineering Applications, Lect. Notes in Computer Science, vol. 2085, part II, pages 55-63, 2001. Springer-Verlag.

      70. E. I. Barakova and U. R. Zimmer Dynamical Situation and Trajectory Discrimination by Means of Clustering and Summation of Raw Range Measurements [847 KB pdf]. International Conference on Advances in Intelligent Systems: Theory and Application -AISTA 2000, pages 1-6, 2000. Canberra Australia.

      71. E. I. Barakova Learning Reliability: a study on indecisiveness in sample selection [3687 KB pdf]. PrintPartners Ipskamp B.V. ISBN 90-367-0987-3, March 1999.

        Preface

        The design of a product is based on the assumption of how it will be used. Conversely, the product is usually good for only such usage as was assumed during its conception. In a classical sense, the implicit assumption brings an explicit specification from which the design is derived. More often than not, the specification is therefore the starting point of a hopefully structured and wellŸ_"behaved, but eventually mechanical design effort. Where the customer tends to learn from the design and mandates to change and/or augment the specification during the process, the project planning gets invalidated. Current practice is therefore to fix the specification in advance, for instance by contract.
        The interest in Artificial Neural Networks (ANN) is founded on their ability to learn from examples, as derived from the environment in which the product will operate, instead of being designed from an hypothesis about the operation. It is commonly agreed that learning is based on memorization (associating or mapping a set of questions to their answers) and generalization (the ability to answer new questions about the same problem). As such, ANNs promise a perfect fit to their intended usage. But circumstantial evidence still does not equal a witness observation. Despite its historic fame, an Artificial Neural Network will not learn all, let alone under all circumstances. This is probably the most striking difference with a designed product: there will never be a proof by construction!
        With the coming of age of neural technology, an impressive number of neural products have found their way to the market place [88]. Some popular applications are indicated in figure 1, which position them in the area spanned by computational complexity and model correctness. The bars indicate the achieved performance: the patterns within the bar indicate the widely achieved results, since the white part stands for the best results in the area. Clearly, none of them achieves a 100% correct functionality. It appears, that for each application a bottom level of functionality can be reached almost without any effort. However, to go beyond requires special attention and has therefore spurred a lot of research to develop new algorithms, to construct alternative architectures, to provide different settings of input parameters or to preprocess input data.
        To achieve a product of ultimate performance, two methods can be devised: (a) its function is based on a provably correct algorithm, and (b) an effective redundancy is to be incorporated in the underlying algorithm. As far as ANNs are constructed from analysis of noisy data, they can entirely be considered as systems of the second type. Because statistics is concerned with data analysis as well, there is a considerable overlap between the fields of neural networks and statistics. To analyze learning and generalization of neural networks from noisy/randomized data, statistical inference can also be used.
        Performance enhancement can be created by a kind of majority voting. This principle suggests that, instead of providing one neural network solution to a problem, a set of neural networks can be combined to form a neural net system which performs better than any of the networks on its own [116] [138]. The conclusion made in [112] is that mere redundancy does not necessarily increase reliability. Empirically it is common practice to train many different candidate networks to select the winner on basis of predefined criteria. A disadvantage of this method is that training of the losing networks does not help in a further development. Another weak point is that the criterion for choosing the best network is usually the performance on a validation set, which can not guarantee the modeling quality of the underlying data generator. But when the networks are incomplete versions of the same functionality, the combination might raise the functional correctness to a higher level (Figure 2).
        The committee arrangement generalizes this idea. It can have significantly better predictions on new data at an acceptable increase of the computational complexity. The performance of the committee can be much better than the performance of each single network in isolation. The committee contains a set of a trained networks diversified in a distinct way. Diversity can appear in the number of hidden neurons, in the kind of network model, in the mixture of networks, in the optimization criteria, in the initial weight configuration, training parameters in the training samples, etc. The extent to which reliability can be improved by combining neural net solutions depends on the type of diversity, present in the set of nets.
        All such techniques assume that the basic neural network is optimally trained. However, we have noticed that training algorithms are often slow and sometimes unable to converge, even though the underlying techniques often perform very well on other problems. In other words, even though an ANN can be trained to some functionality, there appears to be an underlying problem that causes unreliability in learning. This thesis will therefore be devoted to unravel such circumstances and to contribute ways in which reliable learning can be achieved. By large, the neural paradigm problem is represented as a stream of examples (data) and that guides the learning algorithm to adapt the network parameters until the network is Ÿ_otrainedŸ__ to give the right answers to the posed questions. Thus the success and the reliability of this training depends to a large extent on the content and composition of this data stream.
        Overall unreliable learning can be considered to result from the interaction between three factors: network, problem, and algorithm. In an attempt to answer questions like why and when the learning process will become unreliable and when a systematic failure can appear, backpropagation (still the algorithm with highest practical significance) has been used. The restricted class of architectures it is supposed to be used for and the feedforward architecture allow us to elaborate in more detail on the problem with respect to the chosen architecture and algorithm.
        As we found that the conventional focus on network, problem and algorithm leaves much to be desired, we propose here to base the discussion rather on symmetry, randomness (as basic network design principles), and knowledge (the problem to be learned) as the basic ingredients of the universe of discourse. A high degree of symmetry in the initially designed network is historically viewed to favor the learning algorithm in providing an equal chance to move in several directions. However, this has also a drawback: the freedom of choice may lead to indecisiveness. Admittedly, randomness may in turn help the network escape from such a dilemma. But then again, randomness may wipe away the knowledge; hence a working balance should be found.
        Symmetry can be dominant in the beginning of, but also at specific moments during, learning. Randomness (for instance as stochastic variable in the learning algorithm or as additional noise at the network input, output or internal parameters ) is then required to force the presentation of examples to follow alternative itineraries. When the amount of randomness is not sufficient to counteract symmetry, learning will not be completed: instead of being adapted to ensure the right mapping between input/output data strings, the initial parameters will eventually become zero. If the noise (the randomness) of the system is dominant, learning will also be unsuccessful, because the network will rather learn the noise than the exemplified knowledge. The fundamental issue of learning is therefore the creation of a functional balance between symmetry and randomness directed by the examples (the knowledge).
        To bring this idea into tangible borders, the interaction between learning components is represented in the error surface paradigm. The network will be able to extract the necessary information by adapting itself to map the questions posed to the right answers. This adaptation is in fact an optimization procedure and is thus equivalent to finding the minimum energy state on an error landscape. The steps, that the learning algorithm takes on this landscape, are directed by the presented examples and form a learning trajectory on this surface. Directing this itinerary properly can help to escape some difficulties to pass surface areas, at which the learning algorithm normally spends a lot of time on or from which it can never escape. For finding an optimal trajectory on the error surface, the soŸ_"called regularisation methods have been used. An alternative effect has the introduction of extra noise during training. Our objection here is that the task complexity or the convergence accuracy may be changed in an unwanted direction. The investigation of the statistical longŸ_"run effects of example presentation when traveling on the difficult forms of the global error surface brings us to a constructive algorithm which helps in escaping them.
        Therefore, the work in this thesis takes an alternative route to ensure reliable learning by focussing on sample diversity [116]. On basis of the instantaneous characteristics of the current training set we will conclude on learnability, reorder the set if necessary to establish the best sample sequence and train eventually a single network with success.
        In conclusion, this thesis aims to give directions on how learning can be guaranteed so that its duration will be short and stable and its success unquestionable from the outset. In this respect, we aim to contribute to move neural technology from the realm of Ÿ_oLearning by ExamplesŸ__ to Ÿ_oDesign by ExamplesŸ__.

      72. E. I. Barakova and L. Spaanenburg Windowed Active Sampling for Reliable Neural Learning [1159 KB pdf]. Journal of Systems Architecture, 44:635-650, 1998.

      73. Related work

      74. Maya Dimitrova and Hiroaki Wagatsuma Web Agent Design Based on Computational Memory and Brain Research Information Ectraction from the Internet , Concept press LTD, 2011
      75. L.o.t. Hof, J.d. Pee, J. Sturm, T. Bekker, and J. Verbeek Prolonged play with the ColorFlares: how does open-ended play behavior change over time? Proceedings of the 3rd International Conference on Fun and Games , pp 99-106 2010.
      76. Maya Dimitrova, Chavdar Roumenin, Dimitar Nikolov, David Rotger and Petia Radeva Multimodal Data Fusion for Intelligent Cardiovascular Diagnosis and Treatment in the ActiveVessel Medical Workstation. Journal of Intelligent Systems , Vol. 18, No. 1-2, 2009.
      77. Joep (J.W.) Frens and Kees (C.J.) Overbeeke Setting the stage for the design of highly interactive systems Proceedings of International Association of Societies of Design Research 2009 - IASDR'09. , (pp. 1-10). Seoul, Korea: Korean Society of Design Science.
      78. P. Gnanayutham and M. Dimitrova NOVEL INTERFACES FOR REHABILITATION ROBOTS In the Proc. ofTWENTY - FIRST INTERNATIONAL CONFERENCE "ROBOTICS & MECHATRONICS '11",pp 73-80 19 – 21 SEPTEMBER 2011, VARNA, BULGARIA
      79. Dimitrova, M. SOCIAL SENSOR DESIGN FOR EMBEDDED SYSTEMS Proceedings of the International Workshop on Human-Computer Interaction and eLearning Systems (HCIeLS-2011) pp. 393-400, 15-16 September 2011, BULGARIA [pdf]