Filters








69,690 Hits in 5.2 sec

Learning Generalized Temporal Abstractions across Both Action and Perception

Khimya Khetarpal
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Analogous to temporally extended actions, we propose learning temporally extended perception. The key idea is to learn temporal abstractions unifying both action and perception.  ...  Learning temporal abstractions which are partial solutions to a task and could be reused for other similar or even more complicated tasks is intuitively an ingredient which can help agents to plan, learn  ...  I then worked independently on the derivation and algorithm of this approach which were both reviewed by my advisor.  ... 
doi:10.1609/aaai.v33i01.33019890 fatcat:hvlravevwvhrhpwvxxy4g2mmvm

Swinging in the brain: shared neural substrates for behaviors related to sequencing and music

Petr Janata, Scott T Grafton
2003 Nature Neuroscience  
Because of the intimate coupling between perception and action, music provides a panoramic window through which we can examine the neural organization of complex behaviors that are at the core of human  ...  Here we review neuroimaging studies of explicit sequence learning and temporal production-findings that ultimately lay the groundwork for understanding how more complex musical sequences are represented  ...  Box 1 Music we encounter (and sequences in general) range widely in both temporal and ordinal complexity.  ... 
doi:10.1038/nn1081 pmid:12830159 fatcat:k5nrsuhkunajzksr6katoy6yue

Motor cognition–motor semantics: Action perception theory of cognition and communication

Friedemann Pulvermüller, Rachel L. Moseley, Natalia Egorova, Zubaida Shebani, Véronique Boulenger
2014 Neuropsychologia  
A new perspective on cognition views cortical cell assemblies linking together knowledge about actions and perceptions not only as the vehicles of integrated action and perception processing but, furthermore  ...  brain imaging and other experimental data documenting the role of action perception circuits in cognition, language and communication.  ...  the Engineering and Physical Sciences Research Council (UK) (BABEL grant).  ... 
doi:10.1016/j.neuropsychologia.2013.12.002 pmid:24333695 fatcat:siuyrfpbsvgmlmdzx3xud5f6fu

Effects of altered auditory feedback across effector systems: Production of melodies by keyboard and singing

Peter Q. Pfordresher, James T. Mantell
2012 Acta Psychologica  
increased error rates, and the effect of asynchronous feedback was similar in magnitude across tasks.  ...  These results support the view that disruption from AAF is based on abstract, effector independent, response-effect associations but that the strength of associations differs across effector systems.  ...  We are grateful to Anastasiya Kobrina for help with data analysis and to Thomas Varco who arranged the singing AAF paradigm.  ... 
doi:10.1016/j.actpsy.2011.10.009 pmid:22100135 fatcat:d3ajzuq77ra63ilogsde2wblay

Page 320 of Dsh Abstracts Vol. 14, Issue 2 [page]

1974 Dsh Abstracts  
Criticizes generative phonology and, to some extent, generative transformational linguistics in general, for its extreme process model, intuitively unacceptable underlying abstractions, its lack of synchrony  ...  320 dsh ABSTRACTS 1648. HAMMARSTROM, G. (Monash U., Clayton, Victoria 3186 Australia) Generative phonology. A critical appraisal. Phonetica, 27(3), 1973, 157-184.  ... 

Crossmodal Language Grounding in an Embodied Neurocognitive Model [article]

Stefan Heinrich, Yuan Yao, Tobias Hinz, Zhiyuan Liu, Thomas Hummel, Matthias Kerzel, Cornelius Weber, Stefan Wermter
2020 arXiv   pre-print
However, characterising the underlying mechanisms in the brain is difficult and explaining the grounding of language in crossmodal perception and action remains challenging.  ...  The representations self-organise hierarchically and embed temporal and spatial information through composition and decomposition.  ...  FUNDING The authors gratefully acknowledge partial support from the German Research Foundation (DFG) and the National Science Foundation of China (NSFC) under project Crossmodal Learning (TRR-169).  ... 
arXiv:2006.13546v1 fatcat:ok7lhtpparg3ni33bxagjuoyae

Machine Perception and Learning Grand Challenge: Situational Intelligence Using Cross-Sensory Fusion

Shashi Phoha
2014 Frontiers in Robotics and AI  
The notion of context itself is often incoherent and ill-defined across sensing modalities and applications: image processing research generally assumes only the visual scene to be the context for object  ...  These, in turn, limit the power of datadriven abstract reasoning and problemsolving algorithms, cause a lack of focus for drawing upon relevant past knowledge, and inhibit situational learning.  ...  FA9550-12-1-0270 and by the Office of Naval Research (ONR) under Grant No N00014-11-1-0893.  ... 
doi:10.3389/frobt.2014.00007 fatcat:4ihbm6yd3vb7tkwhsvmmwcmowu

Page 771 of Psychological Abstracts Vol. 92, Issue 3 [page]

2005 Psychological Abstracts  
Subjects’ performance improved in both conditions across blocks of practice. A distinct learning effect related to the repeating sequence was also observed.  ...  Correlational and principal factor analyses suggested a common pacemaker-based interval timing mechanism involved in duration discrimination, temporal generalization, and temporal order judgment.  ... 

The case of CAUSE: neurobiological mechanisms for grounding an abstract concept

Friedemann Pulvermüller
2018 Philosophical Transactions of the Royal Society of London. Biological Sciences  
One contribution of 23 to a theme issue 'Varieties of abstract concepts: development, use and representation in the brain'.  ...  The mirror-Piaget model captures both the learning by own action performance, plus observing its (local or distant) consequences, and the learning by observation of other people's actions, too.  ...  This result supports a role of human body action in causal learning from perception.  ... 
doi:10.1098/rstb.2017.0129 pmid:29914997 pmcid:PMC6015827 fatcat:s3y5dc7n65fblmwwvmintzubca

Dissolving the self

George Deane
2020 Philosophy and the Mind Sciences  
Next, a view of the action of psychedelics as lowering the precision of high-level priors within the generative model is unpacked in terms of a high Bayesian learning rate.  ...  Finally, the relaxation of high-level priors is argued to cause a "collapse" in the temporal thickness of the generative model, resulting in a collapse in the self-model and a loss of the ordinary sense  ...  Acknowledgments Thanks very much to Mel Andrews, Andrew Corcoran, and Andy Clark for invaluable critical feedback and discussion in the production of this paper.  ... 
doi:10.33735/phimisci.2020.i.39 fatcat:sregtdmh7jc43gcn5u7xdha3rq

Robot learning with a spatial, temporal, and causal and-or graph

Caiming Xiong, Nishant Shukla, Wenlong Xiong, Song-Chun Zhu
2016 2016 IEEE International Conference on Robotics and Automation (ICRA)  
It unifies both knowledge representation and action planning in the same hierarchical data structure, allowing a robot to expand its spatial, temporal, and causal knowledge at varying levels of abstraction  ...  The learning system can watch human demonstrations, generalize learned concepts, and perform tasks in new environments, across different robotic platforms.  ...  In addition, we would like to thank SRI International and OSRF for their support.  ... 
doi:10.1109/icra.2016.7487364 dblp:conf/icra/XiongSXZ16 fatcat:agdxx2bwbvcf5l43dkldvmt42m

Recognizing Human Actions in the Motion Trajectories of Shapes

Melissa Roemmele, Soja-Marie Morgens, Andrew S. Gordon, Louis-Philippe Morency
2016 Proceedings of the 21st International Conference on Intelligent User Interfaces - IUI '16  
We applied two machine learning approaches, a spatial-temporal bag-of-words model and a recurrent neural network, to the task of automatically recognizing actions in these datasets.  ...  When they asked participants to narrate an animated film of two triangles and a circle moving in and around a box, participants described the shapes' movement in terms of human actions.  ...  In this work, we showed how the high-level perception of human actions in motion trajectories can be modeled using machine learning, specifically by both a spatial-temporal bag-ofwords model and a recurrent  ... 
doi:10.1145/2856767.2856793 dblp:conf/iui/RoemmeleMGM16 fatcat:l6ufnju3rja6vpvs4uf6yqnatm

Delving Deeper into Convolutional Networks for Learning Video Representations [article]

Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville
2016 arXiv   pre-print
We empirically validate our approach on both Human Action Recognition and Video Captioning tasks.  ...  We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).Our method relies on  ...  and CIFAR.  ... 
arXiv:1511.06432v4 fatcat:sdta2srvbjddtgbgztjeswwbt4

Semantic embodiment, disembodiment or misembodiment? In search of meaning in modules and neuron circuits

Friedemann Pulvermüller
2013 Brain and Language  
I thank Alfonso for a good dispute and for helping me sharpen some of the arguments.  ...  This work was supported by the Freie Universität Berlin (startup grant), Deutsche Forschungsgemeinschaft (Excellence Cluster ''Languages of Emotion''), and the EPSRC and BBSRC (BABEL grant ''Brain-inspired  ...  Learning abstract word meaning Arguments for semantic grounding in action and perception are usually made for concrete words and statements used to speak about actions and objects.  ... 
doi:10.1016/j.bandl.2013.05.015 pmid:23932167 fatcat:43saqob6vnhapakpm6kob4xe4u

The Cognitive Representation of Time and Duration

Rolf Ulrich, Anne-Claire Rattat, Ruth Ogden, Hedderik Van Rijn, Daniel Bratzke
2014 Procedia - Social and Behavioral Sciences  
Finally, Daniel Bratzke reviews prominent ideas about how temporal information is coded within and across sensory modalities. The titles and abstracts of the four talks are given below.  ...  Hedderik van Rijn and Niels Taagten show how general principles of memory and attention can be connected with theories about time perception.  ...  In my talk I will show how general principles of memory and attention can connect myopic theories about time perception to a larger framework, and will preview how the development of general reasoning  ... 
doi:10.1016/j.sbspro.2014.02.303 fatcat:pygetdy6fvbqhmnlybdgk5jdle
« Previous Showing results 1 — 15 out of 69,690 results