Filters








277 Hits in 4.3 sec

Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution [article]

Jonas Rothfuss, Fabio Ferreira, Eren Erdal Aksoy, You Zhou, Tamim Asfour
2018 arXiv   pre-print
We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action experiences.  ...  reconstructs original episodes, and 4) predicts future frames in an end-to-end fashion.  ...  The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 641100 (TimeStorm) and from the German Research  ... 
arXiv:1801.04134v3 fatcat:yxjtkvhfynb6hktfm3wvjzpsru

Biologically plausible connectionist prediction of natural language thematic relations

Joao Luis Garcia Rosa
2010 The 2010 International Joint Conference on Neural Networks (IJCNN)  
BioθPred is designed to "predict" thematic (semantic) roles assigned to words in a sentence context, employing biologically inspired training algorithm and architecture, and adopting a psycholinguistic  ...  A third option merges the two previous approaches into a hybrid one: a symbolic thematic theory is used to supply the connectionist network with initial knowledge.  ...  Also, the authors would like to thank the anonymous reviewers for their constructive criticism and useful suggestions.  ... 
doi:10.1109/ijcnn.2010.5596500 dblp:conf/ijcnn/Rosa10 fatcat:icprclvshfcj3aeajnrljvjrsu

Page 3904 of Psychological Abstracts Vol. 82, Issue 8 [page]

1995 Psychological Abstracts  
—Explored a computational model of motion processing in brain area MT based on the observed response properties of cortical neurons that is consistent with the visual perception of partially occluded and  ...  “nonconscious” andsubsymbolic” on the other does not exist. 31413.  ... 

Integrating perceptual and cognitive modeling for adaptive and intelligent human-computer interaction

Z. Duric, W.D. Gray, R. Heishman, Fayin Li, A. Rosenfeld, M.J. Schoelles, C. Schunn, H. Wechsler
2002 Proceedings of the IEEE  
The technology proposed is based on a general four-stage interactive framework, which moves from parsing the raw sensory-motor input, to interpreting the user's motions and emotions, to building an understanding  ...  IHCI integrates parsing and interpretation of nonverbal information with a computational cognitive model of the user, which, in turn, feeds into processes that adapt the interface to enhance operator performance  ...  A very good review of early work on motion understanding approaches and applications was done by Cedras and Shah [17] .  ... 
doi:10.1109/jproc.2002.801449 fatcat:qrhjwv36xndgjcqk6q7u73qg2m

Editorial Commentary

1988 Behavioral and Brain Sciences  
A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models.  ...  The result is a picture in which traditional and connectionist theoretical constructs collaborate intimately to provide an understanding of cognition.  ...  and a symbolic approach.  ... 
doi:10.1017/s0140525x00052791 fatcat:7o7kyja25jfztfovklj74nqt3y

Explainable AI for Intelligence Augmentation in Multi-Domain Operations [article]

Alun Preece, Dave Braines, Federico Cerutti, Tien Pham
2019 arXiv   pre-print
The union of these three elements is intended to show the potential value of a CSU approach in the context of MDO ISR, grounded in three distinct use cases, highlighting how the need for explainability  ...  dense urban terrain analysis, and enhanced asset interoperability; (3) we appraise the state-of-the-art in explainable AI in relation to the vignettes with a focus on human-machine collaboration to achieve  ...  Figure 2 : 2 A multi-agent non-hierarchical approach to CSU: (top) human agent, (bottom left) subsymbolic AI agent, (bottom right) symbolic AI agent.  ... 
arXiv:1910.07563v1 fatcat:vhchx7d5vrgrxf5z6cqu4ea4n4

Specializing Underdetermined Action Descriptions Through Plan Projection [article]

Gayane Kazhoyan, Michael Beetz
2018 arXiv   pre-print
We evaluate our approach by showing how a PR2 robot, when equipped with the proposed system, is able to choose action parameterizations that increase task execution success rates and overall performance  ...  of fetch and deliver actions in a real world setting.  ...  ACKNOWLEDGMENTS This work was supported by DFG Collaborative Research Center Everyday Activity Science and Engineering (EASE) (CRC #1320).  ... 
arXiv:1812.08224v1 fatcat:qqaldyoirff3bokxbex4kftnqi

A Reinforcement Connectionist Approach to Robot Path Finding in Non-Maze-Like Environments [chapter]

José R. Millán, Carme Torras
1992 Reinforcement Learning  
This paper presents a reinforcement connectionist system which finds and learns the suitable situationaction rules so as to generate feasible paths for a point robot in a 2D environment with circular obstacles  ...  Equipped with this strategy and a powerful codification scheme, the path-finder (i) learns quickly, (ii) deals with continuousvalued inputs and outputs, (iii) exhibits good noise-tolerance and generalization  ...  Acknowledgments We thank Rich Sutton whose suggestions have been really valuable for improving the presentation of our work, and Aristide Varfis for helpful discussions.  ... 
doi:10.1007/978-1-4615-3618-5_8 fatcat:ow5dphym7nbqlnsvininp5suky

SAL: an explicitly pluralistic cognitive architecture

David J. Jilk, Christian Lebiere, Randall C. O'Reilly, John R. Anderson
2008 Journal of experimental and theoretical artificial intelligence (Print)  
perception approaches are used.  ...  A pluralistic approach is also being used in a project to combine neural and algorithmic approaches to perception in simulated environments as a replaceable 'front-end' to symbolic cognitive architectures  ... 
doi:10.1080/09528130802319128 fatcat:rrpljyjqh5afvpwl2cw55ritci

Everyday robotic action: lessons from human action control

Roy de Kleijn, George Kachergis, Bernhard Hommel
2014 Frontiers in Neurorobotics  
and subsymbolic planning of action sequences, the integration of feedforward and feedback control, the clustering of complex actions into subcomponents, and the contextualization of action-control structures  ...  This requires the real-time planning and execution of complex, temporally extended sequential actions under high degrees of uncertainty, which provides many challenges to traditional approaches to robot  ...  Compared to typical step-wise robotic motion, this action blending seems to be more efficient, using predictive motion to minimize the time and energy required to achieve the goal.  ... 
doi:10.3389/fnbot.2014.00013 pmid:24672474 pmcid:PMC3956116 fatcat:wbjljqjfmzgo5fpcxvpp4edneu

Levels of description and explanation in cognitive science

William Bechtel
1994 Minds and Machines  
The use of the three different names sometimes interchangeably and sometimes distinctively revels that there is a fair amount of disagreement as to how to answer this question.  ...  cognitive theories attempt to function: One is drawn from too low a level, the other from too high a level.  ...  perception are analyzed and understood in a way that is independent of the particular mechanisms and structures that implement them in our heads.  ... 
doi:10.1007/bf00974201 fatcat:eu4x3z2zyjd5vn7zj6nofl4n4e

A PSYCHOGENETIC ALGORITHM FOR BEHAVIORAL SEQUENCE LEARNING

VITTORIO MANIEZZO, MATTEO ROFFILLI
2007 International journal on artificial intelligence tools  
Further, we discussed the possible parallels between our model and subsymbolic machine learning and neuroscience.  ...  These results are to be considered as a feasibility study for a more general project aimed at developing a cognitively wellfounded approach and at the definition of new algorithms for unsupervised learning  ...  and motion.  ... 
doi:10.1142/s021821300700328x fatcat:l6ex6qif2rdvzagik5miz22fle

A reinforcement connectionist approach to robot path finding in non-maze-like environments

Jos� Del R. Mill�n, Carme Torras
1992 Machine Learning  
This paper presents a reinforcement connectionist system which finds and learns the suitable situationaction rules so as to generate feasible paths for a point robot in a 2D environment with circular obstacles  ...  Equipped with this strategy and a powerful codification scheme, the path-finder (i) learns quickly, (ii) deals with continuousvalued inputs and outputs, (iii) exhibits good noise-tolerance and generalization  ...  Acknowledgments We thank Rich Sutton whose suggestions have been really valuable for improving the presentation of our work, and Aristide Varfis for helpful discussions.  ... 
doi:10.1007/bf00992702 fatcat:gono2whhvrfepl6tx22uulkcim

ACT-R/E: An Embodied Cognitive Architecture for Human-Robot Interaction

Greg Trafton, Laura Hiatt, Anthony Harrison, Frank Tanborello, Sangeet Khemlani, Alan Schultz
2013 Journal of Human-Robot Interaction  
Then, we leverage that knowledge of people by using it to predict what a person will do in different situations; e.g., that a person may forget something and may need to be reminded or that a person cannot  ...  We also discuss methods of how to evaluate a cognitive architecture and show numerous empirically validated examples of ACT-R/E models.  ...  The views and conclusions contained in this document do not represent the official policies of the US Navy.  ... 
doi:10.5898/jhri.2.1.trafton fatcat:7jygq5d2gbcalexani7dhzpmh4

Challenges in Understanding Visual Shape Perception and Representation: Bridging Subsymbolic and Symbolic Coding [chapter]

Philip J. Kellman, Patrick Garrigan, Gennady Erlikhman
2013 Shape Perception in Human and Computer Vision  
At a more abstract level, experimental data and computational models have revealed a great deal about contour, object, and shape perception.  ...  Successful perception, thought and action depend on processes that produce accurate descriptions of these objects and events.  ...  Acknowledgements We thank Brian Keane, Evan Palmer, and Hongjing Lu for helpful discussions and Rachel Older for general assistance.  ... 
doi:10.1007/978-1-4471-5195-1_18 fatcat:xaq7ufc4ffcahllox4yi3wbiai
« Previous Showing results 1 — 15 out of 277 results