FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1525334932> ?p ?o ?g. }

• W1525334932 abstract "Training an agent to operate in an environment whose mappings are largely unknown is generally recognized to be exceptionally difficult. Further, granting such a learning agent the ability to produce an appropriate sequence of actions entirely from a single input stimulus remains a key problem. Various reinforcement learning techniques have been utilized to handle such learning tasks, but convergence to optimal policies is not guaranteed for many of these methods. Traditional supervised learning methods hold more assurances of convergence, but these methods are not well suited for tasks where desired actions in the output space of the learner, termed proximal actions, are not available for training. Rather, target outputs from the environment are distal from where the learning takes place. For example, a child acquiring language skill who makes speech errors must learn to correct them based on heard information that reaches his/her auditory cortex, which is distant from the motor cortical regions that control speech output. While distal supervised learning techniques for neural networks have been devised, it remains to be established how they can be trained to produce sequences of proximal actions from only a single static input.The architecture demonstrated here incorporates recurrent multi-layered neural networks, each maintaining some manner of memory in the form of a context vector, into the distal supervised learning framework. This enables it to train learners capable of generating correct proximal sequences from single static input stimuli. This is in contrast to existing distal learning methods designed for non-recurrent neural network learners that utilize no concept of memory of their prior behavior. Also, a technique known as teacher forcing was adapted for use in distal sequential learning settings which is shown to result in more efficient usage of the recurrent neural network's context layer. The effectiveness of this approach is demonstrated by applying it in training recurrent learners to acquire phoneme sequence generating behavior using only previously heard and stored auditory phoneme sequences. The results indicate that recurrent networks can be integrated with distal learning methods to create effective sequence generators even when constantly updating current state information is unavailable." @default.
• W1525334932 created "2016-06-24" @default.
• W1525334932 creator A5013248069 @default.
• W1525334932 creator A5050009555 @default.
• W1525334932 date "2007-01-01" @default.
• W1525334932 modified "2023-09-23" @default.
• W1525334932 title "Neural network generation of temporal sequences from single static vector inputs using varying length distal target sequences" @default.
• W1525334932 cites W1488621072 @default.
• W1525334932 cites W1510635315 @default.
• W1525334932 cites W1541007220 @default.
• W1525334932 cites W1542722502 @default.
• W1525334932 cites W1557842000 @default.
• W1525334932 cites W1562361696 @default.
• W1525334932 cites W1569296262 @default.
• W1525334932 cites W1603077448 @default.
• W1525334932 cites W1640360522 @default.
• W1525334932 cites W1674799117 @default.
• W1525334932 cites W169429238 @default.
• W1525334932 cites W1804997726 @default.
• W1525334932 cites W1966952435 @default.
• W1525334932 cites W197326900 @default.
• W1525334932 cites W1975346765 @default.
• W1525334932 cites W1986370058 @default.
• W1525334932 cites W1989584886 @default.
• W1525334932 cites W2007181247 @default.
• W1525334932 cites W2010800472 @default.
• W1525334932 cites W2016589492 @default.
• W1525334932 cites W2032139276 @default.
• W1525334932 cites W2032629007 @default.
• W1525334932 cites W2038111264 @default.
• W1525334932 cites W2041367235 @default.
• W1525334932 cites W2043968544 @default.
• W1525334932 cites W2045031658 @default.
• W1525334932 cites W2052117683 @default.
• W1525334932 cites W2055877435 @default.
• W1525334932 cites W2057653135 @default.
• W1525334932 cites W2067183756 @default.
• W1525334932 cites W2085654611 @default.
• W1525334932 cites W2086789740 @default.
• W1525334932 cites W2091565802 @default.
• W1525334932 cites W2098398123 @default.
• W1525334932 cites W2100677568 @default.
• W1525334932 cites W2103617625 @default.
• W1525334932 cites W2107726111 @default.
• W1525334932 cites W2110485445 @default.
• W1525334932 cites W2114414717 @default.
• W1525334932 cites W2121863487 @default.
• W1525334932 cites W2123716044 @default.
• W1525334932 cites W2124776405 @default.
• W1525334932 cites W2125848004 @default.
• W1525334932 cites W2138178898 @default.
• W1525334932 cites W2143908786 @default.
• W1525334932 cites W2143956139 @default.
• W1525334932 cites W2147591409 @default.
• W1525334932 cites W2147677349 @default.
• W1525334932 cites W2150355110 @default.
• W1525334932 cites W2154890045 @default.
• W1525334932 cites W2157148561 @default.
• W1525334932 cites W2160328559 @default.
• W1525334932 cites W2766736793 @default.
• W1525334932 cites W2798711040 @default.
• W1525334932 cites W2974832207 @default.
• W1525334932 cites W3011120880 @default.
• W1525334932 cites W3133056632 @default.
• W1525334932 cites W3139377883 @default.
• W1525334932 cites W3198350258 @default.
• W1525334932 cites W65738273 @default.
• W1525334932 cites W1979219638 @default.
• W1525334932 cites W2066783003 @default.
• W1525334932 cites W2094790441 @default.
• W1525334932 hasPublicationYear "2007" @default.
• W1525334932 type Work @default.
• W1525334932 sameAs 1525334932 @default.
• W1525334932 citedByCount "0" @default.
• W1525334932 crossrefType "dissertation" @default.
• W1525334932 hasAuthorship W1525334932A5013248069 @default.
• W1525334932 hasAuthorship W1525334932A5050009555 @default.
• W1525334932 hasConcept C119857082 @default.
• W1525334932 hasConcept C136389625 @default.
• W1525334932 hasConcept C147168706 @default.
• W1525334932 hasConcept C151730666 @default.
• W1525334932 hasConcept C154945302 @default.
• W1525334932 hasConcept C2779343474 @default.
• W1525334932 hasConcept C28490314 @default.
• W1525334932 hasConcept C40506919 @default.
• W1525334932 hasConcept C40567965 @default.
• W1525334932 hasConcept C41008148 @default.
• W1525334932 hasConcept C50644808 @default.
• W1525334932 hasConcept C86803240 @default.
• W1525334932 hasConcept C97541855 @default.
• W1525334932 hasConceptScore W1525334932C119857082 @default.
• W1525334932 hasConceptScore W1525334932C136389625 @default.
• W1525334932 hasConceptScore W1525334932C147168706 @default.
• W1525334932 hasConceptScore W1525334932C151730666 @default.
• W1525334932 hasConceptScore W1525334932C154945302 @default.
• W1525334932 hasConceptScore W1525334932C2779343474 @default.
• W1525334932 hasConceptScore W1525334932C28490314 @default.
• W1525334932 hasConceptScore W1525334932C40506919 @default.
• W1525334932 hasConceptScore W1525334932C40567965 @default.
• W1525334932 hasConceptScore W1525334932C41008148 @default.

• next