Matches in SemOpenAlex for { <https://semopenalex.org/work/W192378942> ?p ?o ?g. }
- W192378942 endingPage "268" @default.
- W192378942 startingPage "219" @default.
- W192378942 abstract "In this chapter we provide mathematical models for a general memory structure and for sensory-motor control via perception, detailing on some of the Recurrent Neural Networks (RNNs) introduced in Chapter 4. In the first section we study how individual memory items are stored assuming that situations given in the environment can be represented in the form of synaptic-like couplings in recurrent neural networks (RNN). We provide a theoretical basis concerning the learning process convergence and the network response to novel stimuli. We show that a nD network can learn static and dynamic patterns and can also replicate a sequence of up to n different vectors or frames. Such networks can also perform arithmetic calculations by means of pattern completion. In the second section we introduce a robot platform including the simplest probabilistic sensory and motor layers. Then we use the platform as a test-bed for evaluating the capabilities of robot navigation with different neural networks. We show that the basic robot element, the short-time memory, is the key element in obstacle avoidance. However, in the simplest conditions of no obstacles the straightforward memoryless robot is usually superior in performance. Accordingly, we suggest that small organisms (or agents) with short life-time do not require complex brains and even can benefit from simple brain-like (reflex) structures. In section 3 we propose a memotaxis strategy for target searching, which requires minimal computational resources and can be easily implemented in hardware. The strategy makes use of a dynamical system modeling short time memory which “collects” information on successful steps and corrects decisions made by a gradient strategy. Thus a memotactic robot can take steps against the chemotactic-like sensory gradient. We show (theoretically and experimentally) that the memotaxis strategy effectively suppresses stochasticity observed in the behavior of chemotactic robots in the region of low SNR and provides from 50 to 200% performance gain." @default.
- W192378942 created "2016-06-24" @default.
- W192378942 creator A5008532891 @default.
- W192378942 creator A5040367985 @default.
- W192378942 creator A5055790704 @default.
- W192378942 creator A5072178981 @default.
- W192378942 creator A5087999746 @default.
- W192378942 date "2008-12-18" @default.
- W192378942 modified "2023-10-01" @default.
- W192378942 title "Mathematical Approach to Sensory Motor Control and Memory" @default.
- W192378942 cites W1490290909 @default.
- W192378942 cites W1583901624 @default.
- W192378942 cites W1666326031 @default.
- W192378942 cites W1910745944 @default.
- W192378942 cites W1998909804 @default.
- W192378942 cites W2022029210 @default.
- W192378942 cites W2024184910 @default.
- W192378942 cites W2026152774 @default.
- W192378942 cites W2027951246 @default.
- W192378942 cites W2032535902 @default.
- W192378942 cites W2046695302 @default.
- W192378942 cites W2054311845 @default.
- W192378942 cites W2070174786 @default.
- W192378942 cites W2071980253 @default.
- W192378942 cites W2073573937 @default.
- W192378942 cites W2089029564 @default.
- W192378942 cites W2093912891 @default.
- W192378942 cites W2097856935 @default.
- W192378942 cites W2111438519 @default.
- W192378942 cites W2112246162 @default.
- W192378942 cites W2112575028 @default.
- W192378942 cites W2114476723 @default.
- W192378942 cites W2118706537 @default.
- W192378942 cites W2122741244 @default.
- W192378942 cites W2125409550 @default.
- W192378942 cites W2128084896 @default.
- W192378942 cites W2130012086 @default.
- W192378942 cites W2151351982 @default.
- W192378942 cites W4234824781 @default.
- W192378942 cites W4244987567 @default.
- W192378942 cites W4249526317 @default.
- W192378942 cites W4254816979 @default.
- W192378942 doi "https://doi.org/10.1007/978-3-540-88464-4_5" @default.
- W192378942 hasPublicationYear "2008" @default.
- W192378942 type Work @default.
- W192378942 sameAs 192378942 @default.
- W192378942 citedByCount "1" @default.
- W192378942 countsByYear W1923789422021 @default.
- W192378942 crossrefType "book-chapter" @default.
- W192378942 hasAuthorship W192378942A5008532891 @default.
- W192378942 hasAuthorship W192378942A5040367985 @default.
- W192378942 hasAuthorship W192378942A5055790704 @default.
- W192378942 hasAuthorship W192378942A5072178981 @default.
- W192378942 hasAuthorship W192378942A5087999746 @default.
- W192378942 hasConcept C111472728 @default.
- W192378942 hasConcept C111919701 @default.
- W192378942 hasConcept C138885662 @default.
- W192378942 hasConcept C147168706 @default.
- W192378942 hasConcept C154945302 @default.
- W192378942 hasConcept C15744967 @default.
- W192378942 hasConcept C180747234 @default.
- W192378942 hasConcept C2780586882 @default.
- W192378942 hasConcept C41008148 @default.
- W192378942 hasConcept C50644808 @default.
- W192378942 hasConcept C90509273 @default.
- W192378942 hasConcept C94487597 @default.
- W192378942 hasConcept C98045186 @default.
- W192378942 hasConceptScore W192378942C111472728 @default.
- W192378942 hasConceptScore W192378942C111919701 @default.
- W192378942 hasConceptScore W192378942C138885662 @default.
- W192378942 hasConceptScore W192378942C147168706 @default.
- W192378942 hasConceptScore W192378942C154945302 @default.
- W192378942 hasConceptScore W192378942C15744967 @default.
- W192378942 hasConceptScore W192378942C180747234 @default.
- W192378942 hasConceptScore W192378942C2780586882 @default.
- W192378942 hasConceptScore W192378942C41008148 @default.
- W192378942 hasConceptScore W192378942C50644808 @default.
- W192378942 hasConceptScore W192378942C90509273 @default.
- W192378942 hasConceptScore W192378942C94487597 @default.
- W192378942 hasConceptScore W192378942C98045186 @default.
- W192378942 hasLocation W1923789421 @default.
- W192378942 hasOpenAccess W192378942 @default.
- W192378942 hasPrimaryLocation W1923789421 @default.
- W192378942 hasRelatedWork W1971282125 @default.
- W192378942 hasRelatedWork W2026267843 @default.
- W192378942 hasRelatedWork W2056791316 @default.
- W192378942 hasRelatedWork W2065811088 @default.
- W192378942 hasRelatedWork W2210787820 @default.
- W192378942 hasRelatedWork W2293000486 @default.
- W192378942 hasRelatedWork W2527459149 @default.
- W192378942 hasRelatedWork W2557101640 @default.
- W192378942 hasRelatedWork W2589532588 @default.
- W192378942 hasRelatedWork W2593552556 @default.
- W192378942 hasRelatedWork W2617657205 @default.
- W192378942 hasRelatedWork W2949272673 @default.
- W192378942 hasRelatedWork W2995822731 @default.
- W192378942 hasRelatedWork W3022218535 @default.
- W192378942 hasRelatedWork W3044669068 @default.