his.sePublikasjoner
Endre søk
Begrens søket
1 - 6 of 6
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Treff pr side
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
Merk
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Billing, Erik
    et al.
    Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    Lowe, Robert
    Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. Department of Applied IT, University of Gothenburg, Sweden.
    Sandamirskaya, Yulia
    Institute of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland.
    Simultaneous Planning and Action: Neural-dynamic Sequencing of Elementary Behaviors in Robot Navigation2015Inngår i: Adaptive Behavior, ISSN 1059-7123, E-ISSN 1741-2633, Vol. 23, nr 5, s. 243-264Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    A technique for Simultaneous Planning and Action (SPA) based on Dynamic Field Theory (DFT) is presented. The model builds on previous workon representation of sequential behavior as attractors in dynamic neural fields. Here, we demonstrate how chains of competing attractors can be used to represent dynamic plans towards a goal state. The presentwork can be seen as an addition to a growing body of work that demonstratesthe role of DFT as a bridge between low-level reactive approachesand high-level symbol processing mechanisms. The architecture is evaluatedon a set of planning problems using a simulated e-puck robot, including analysis of the system's behavior in response to noise and temporary blockages ofthe planned route. The system makes no explicit distinction betweenplanning and execution phases, allowing continuous adaptation of the planned path. The proposed architecture exploits the DFT property of stability in relation to noise and changes in the environment. The neural dynamics are also exploited such that stay-or-switch action selection emerges where blockage of a planned path occurs: stay until the transient blockage is removed versus switch to an alternative route to the goal.

    Fulltekst (pdf)
    Billing-etal-2015-SPA
  • 2.
    Lowe, Robert
    et al.
    Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. University of Gothenburg, Sweden.
    Barakova, Emilia
    Eindhoven University of Technology, The Netherlands.
    Billing, Erik
    Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    Broekens, Joost
    Delft University of Technology, The Netherlands.
    Grounding emotions in robots: An introduction to the special issue2016Inngår i: Adaptive Behavior, ISSN 1059-7123, E-ISSN 1741-2633, Vol. 24, nr 5, s. 263-266Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Robots inhabiting human environments need to act in relation to their own experience and embodiment as well as to social and emotional aspects. Robots that learn, act upon and incorporate their own experience and perception of others’ emotions into their responses make not only more productive artificial agents but also agents with whom humans can appropriately interact. This special issue seeks to address the significance of grounding of emotions in robots in relation to aspects of physical and homeostatic interaction in the world at an individual and social level. Specific questions concern: How can emotion and social interaction be grounded in the behavioral activity of the robotic system? Is a robot able to have intrinsic emotions? How can emotions, grounded in the embodiment of the robot, facilitate individually and socially adaptive behavior to the robot? This opening chapter provides an introduction to the articles that comprise this special issue and briefly discusses their relationship to grounding emotions in robots.

  • 3.
    Lowe, Robert
    et al.
    Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. Göteborgs Universitet, Tillämpad IT.
    Billing, Erik
    Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    Affective-Associative Two-Process theory: A neural network investigation of adaptive behaviour in differential outcomes training2017Inngår i: Adaptive Behavior, ISSN 1059-7123, E-ISSN 1741-2633, Vol. 25, nr 1, s. 5-23Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In this article we present a novel neural network implementation of Associative Two-Process (ATP) theory based on an Actor–Critic-like architecture. Our implementation emphasizes the affective components of differential reward magnitude and reward omission expectation and thus we model Affective-Associative Two-Process theory (Aff-ATP). ATP has been used to explain the findings of differential outcomes training (DOT) procedures, which emphasize learning differentially valuated outcomes for cueing actions previously associated with those outcomes. ATP hypothesizes the existence of a ‘prospective’ memory route through which outcome expectations can bring to bear on decision making and can even substitute for decision making based on the ‘retrospective’ inputs of standard working memory. While DOT procedures are well recognized in the animal learning literature they have not previously been computationally modelled. The model presented in this article helps clarify the role of ATP computationally through the capturing of empirical data based on DOT. Our Aff-ATP model illuminates the different roles that prospective and retrospective memory can have in decision making (combining inputs to action selection functions). In specific cases, the model’s prospective route allows for adaptive switching (correct action selection prior to learning) following changes in the stimulus–response–outcome contingencies.

  • 4.
    Montebelli, Alberto
    et al.
    Högskolan i Skövde, Institutionen för kommunikation och information. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    Herrera, Carlos
    Högskolan i Skövde, Institutionen för kommunikation och information. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    Ziemke, Tom
    Högskolan i Skövde, Institutionen för kommunikation och information. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    On Cognition as Dynamical Coupling: An Analysis of Behavioral Attractor Dynamics2008Inngår i: Adaptive Behavior, ISSN 1059-7123, E-ISSN 1741-2633, Vol. 16, nr 2-3, s. 182-195Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    The interaction of brain, body, and environment can result incomplex behavior with rich dynamics, even for relatively simpleagents. Such dynamics are, however, often difficult to analyze.In this article, we explore the case of a simple simulated roboticagent, equipped with a reactive neurocontroller and an energylevel, which the agent has been evolved to recharge. A dynamicalsystems analysis shows that a non-neural internal state (energylevel), despite its simplicity, dynamically modulates the behavioralattractors of the agent—environment system, such thatthe robot's behavioral repertoire is continually adapted toits current situation and energy level. What emerges is a dynamic,non-deterministic, and highly self-organized action selectionmechanism, originating from the dynamical coupling of four systems(non-neural internal states, neurocontroller, body, and environment)operating at very different timescales.

    Fulltekst (pdf)
    FULLTEXT01
  • 5.
    Svensson, Henrik
    et al.
    Högskolan i Skövde, Institutionen för kommunikation och information. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    Thill, Serge
    Högskolan i Skövde, Institutionen för kommunikation och information. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    Ziemke, Tom
    Högskolan i Skövde, Institutionen för kommunikation och information. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    Dreaming of electric sheep?: Exploring the functions of dream-like mechanisms in the development of mental imagery simulations2013Inngår i: Adaptive Behavior, ISSN 1059-7123, E-ISSN 1741-2633, Vol. 21, nr 4, s. 222-238Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    According to the simulation hypothesis, mental imagery can be explained in terms of predictive chains of simulated perceptions and actions, i.e., perceptions and actions are reactivated internally by our nervous system to be used in mental imagery and other cognitive phenomena. Our previous research shows that it is possible but not trivial to develop simulations in robots based on the simulation hypothesis. While there are several previous approaches to modelling mental imagery and related cognitive abilities, the origin of such internal simulations has hardly been addressed. The inception of simulation (InSim) hypothesis suggests that dreaming has a function in the development of simulations by forming associations between experienced, non-experienced but realistic, and even unrealistic perceptions. Here, we therefore develop an experimental set-up based on a simple simulated robot to test whether such dream-like mechanisms can be used to instruct research into the development of simulations and mental imagery-like abilities. Specifically, the hypothesis is that dreams' informing the construction of simulations lead to faster development of good simulations during waking behaviour. The paper presents initial results in favour of the hypothesis.

  • 6.
    Windridge, David
    et al.
    Department of Computer Science, Middlesex University, UK / Centre for Vision, Speech and Signal Processing, University of Surrey, UK.
    Svensson, Henrik
    Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
    Thill, Serge
    Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. Donders Institute for Brain, Cognition, and Behaviour, Radboud University, Netherlands.
    On the utility of dreaming: A general model for how learning in artificial agents can benefit from data hallucination2020Inngår i: Adaptive Behavior, ISSN 1059-7123, E-ISSN 1741-2633, artikkel-id UNSP 1059712319896489Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    We consider the benefits of dream mechanisms - that is, the ability to simulate new experiences based on past ones - in a machine learning context. Specifically, we are interested in learning for artificial agents that act in the world, and operationalize "dreaming" as a mechanism by which such an agent can use its own model of the learning environment to generate new hypotheses and training data. We first show that it is not necessarily a given that such a data-hallucination process is useful, since it can easily lead to a training set dominated by spurious imagined data until an ill-defined convergence point is reached. We then analyse a notably successful implementation of a machine learning-based dreaming mechanism by Ha and Schmidhuber (Ha, D., & Schmidhuber, J. (2018). World models. arXiv e-prints, arXiv:1803.10122). On that basis, we then develop a general framework by which an agent can generate simulated data to learn from in a manner that is beneficial to the agent. This, we argue, then forms a general method for an operationalized dream-like mechanism. We finish by demonstrating the general conditions under which such mechanisms can be useful in machine learning, wherein the implicit simulator inference and extrapolation involved in dreaming act without reinforcing inference error even when inference is incomplete.

    Fulltekst (pdf)
    fulltext
1 - 6 of 6
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf