Matches in SemOpenAlex for { <https://semopenalex.org/work/W2734535294> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2734535294 abstract "In artificial intelligence, many tasks of speech recognition, video analysis, and language processing involve temporal processing where the outputs depend on not only spatial contents of the current sensory input frame, but also the relevant context in the attended past. It is illusive how brains use temporal contexts. Many computer methods, such as Hidden Markov chains and recurrent neural networks, require the human programmer to handcraft contexts as symbolic contexts. It has been proved that our Developmental Networks (DN) are capable of learning any emergent Turing Machine (TM), their states have been supervised by human teachers as patterns. This demands much effort from the human trainer. In this paper, we study how agent actions are natural sources of contexts. In humans, muscle actions correspond to the firings of muscle neurons. They are dense in time and correlated with the cognitive skills of the individual. Some actions are meant to handle time warping, while others are not (e.g., for time duration counting). We model actions as dense action patterns. We experimented with DN for recognition of audio sequences as an example of modality, but the principles are modality independent. Our experimental results showed how taking dense, frame-wise actions as contexts helps DN to generate temporal contexts. This work is a necessary step toward our goal to enable machines to autonomously generate contexts as actions through life-long development." @default.
- W2734535294 created "2017-07-21" @default.
- W2734535294 creator A5026274398 @default.
- W2734535294 creator A5074920063 @default.
- W2734535294 date "2017-05-01" @default.
- W2734535294 modified "2023-10-17" @default.
- W2734535294 title "Actions as contexts" @default.
- W2734535294 cites W1637570796 @default.
- W2734535294 cites W1654281207 @default.
- W2734535294 cites W1997798784 @default.
- W2734535294 cites W2009562705 @default.
- W2734535294 cites W2049765399 @default.
- W2734535294 cites W2117130368 @default.
- W2734535294 cites W2117671523 @default.
- W2734535294 cites W2128160875 @default.
- W2734535294 cites W2131472500 @default.
- W2734535294 cites W2141794189 @default.
- W2734535294 cites W2143612262 @default.
- W2734535294 cites W2144165558 @default.
- W2734535294 cites W2148308132 @default.
- W2734535294 cites W2152239535 @default.
- W2734535294 cites W2163362738 @default.
- W2734535294 cites W2178701884 @default.
- W2734535294 cites W241601224 @default.
- W2734535294 cites W2555025701 @default.
- W2734535294 cites W590264144 @default.
- W2734535294 cites W2101094742 @default.
- W2734535294 doi "https://doi.org/10.1109/ijcnn.2017.7965857" @default.
- W2734535294 hasPublicationYear "2017" @default.
- W2734535294 type Work @default.
- W2734535294 sameAs 2734535294 @default.
- W2734535294 citedByCount "2" @default.
- W2734535294 countsByYear W27345352942018 @default.
- W2734535294 countsByYear W27345352942019 @default.
- W2734535294 crossrefType "proceedings-article" @default.
- W2734535294 hasAuthorship W2734535294A5026274398 @default.
- W2734535294 hasAuthorship W2734535294A5074920063 @default.
- W2734535294 hasConcept C107457646 @default.
- W2734535294 hasConcept C121332964 @default.
- W2734535294 hasConcept C126042441 @default.
- W2734535294 hasConcept C151730666 @default.
- W2734535294 hasConcept C154945302 @default.
- W2734535294 hasConcept C194995250 @default.
- W2734535294 hasConcept C23224414 @default.
- W2734535294 hasConcept C2779343474 @default.
- W2734535294 hasConcept C2780226545 @default.
- W2734535294 hasConcept C2780791683 @default.
- W2734535294 hasConcept C41008148 @default.
- W2734535294 hasConcept C62520636 @default.
- W2734535294 hasConcept C76155785 @default.
- W2734535294 hasConcept C86803240 @default.
- W2734535294 hasConceptScore W2734535294C107457646 @default.
- W2734535294 hasConceptScore W2734535294C121332964 @default.
- W2734535294 hasConceptScore W2734535294C126042441 @default.
- W2734535294 hasConceptScore W2734535294C151730666 @default.
- W2734535294 hasConceptScore W2734535294C154945302 @default.
- W2734535294 hasConceptScore W2734535294C194995250 @default.
- W2734535294 hasConceptScore W2734535294C23224414 @default.
- W2734535294 hasConceptScore W2734535294C2779343474 @default.
- W2734535294 hasConceptScore W2734535294C2780226545 @default.
- W2734535294 hasConceptScore W2734535294C2780791683 @default.
- W2734535294 hasConceptScore W2734535294C41008148 @default.
- W2734535294 hasConceptScore W2734535294C62520636 @default.
- W2734535294 hasConceptScore W2734535294C76155785 @default.
- W2734535294 hasConceptScore W2734535294C86803240 @default.
- W2734535294 hasLocation W27345352941 @default.
- W2734535294 hasOpenAccess W2734535294 @default.
- W2734535294 hasPrimaryLocation W27345352941 @default.
- W2734535294 hasRelatedWork W1882167450 @default.
- W2734535294 hasRelatedWork W1971656544 @default.
- W2734535294 hasRelatedWork W2061022289 @default.
- W2734535294 hasRelatedWork W2166110729 @default.
- W2734535294 hasRelatedWork W2326441763 @default.
- W2734535294 hasRelatedWork W2340931095 @default.
- W2734535294 hasRelatedWork W2699505375 @default.
- W2734535294 hasRelatedWork W2725133679 @default.
- W2734535294 hasRelatedWork W2798711578 @default.
- W2734535294 hasRelatedWork W2804740725 @default.
- W2734535294 hasRelatedWork W2912997088 @default.
- W2734535294 hasRelatedWork W2955515643 @default.
- W2734535294 hasRelatedWork W2972172779 @default.
- W2734535294 hasRelatedWork W2977864735 @default.
- W2734535294 hasRelatedWork W3010625385 @default.
- W2734535294 hasRelatedWork W3094678614 @default.
- W2734535294 hasRelatedWork W3117476796 @default.
- W2734535294 hasRelatedWork W3162305767 @default.
- W2734535294 hasRelatedWork W2530063287 @default.
- W2734535294 hasRelatedWork W2736672166 @default.
- W2734535294 isParatext "false" @default.
- W2734535294 isRetracted "false" @default.
- W2734535294 magId "2734535294" @default.
- W2734535294 workType "article" @default.