Matches in SemOpenAlex for { <https://semopenalex.org/work/W2579363105> ?p ?o ?g. }
Showing items 1 to 46 of
46
with 100 items per page.
- W2579363105 abstract "We have designed a fully-connected neural network implemented as an analog circuit consisting of 8 neurons and 64 synapses that can learn rules of 2-by-2 Sudoku or Sudoku-like puzzles and then can solve them. In this circuit, learning is mediated by giving a dopamine reward signal to correct actions, which has a biological basis and is known as reinforcement learning [1]. Regular architecture of the circuit helps it to generalize learned rules and as a consequence expedites the learning procedure. The circuit receives dopamine externally from a trainer circuit and therefore learning is supervised. Injected dopamine will strengthen some of the existing excitatory synapses similar to biological synaptic plasticity [2]. Previously, we had designed a bio-inspired circuit that learns spatiotemporal patterns in an unsupervised mode using structural plasticity. In the human brain, learning is mediated by both types of plasticity [3]. The long-term goal of our research group is combining these two types of plasticity (synaptic and structural) to design a network with higher level of learning capabilities and more complex cognitive skills to imitate the biological brain." @default.
- W2579363105 created "2017-01-26" @default.
- W2579363105 creator A5076860381 @default.
- W2579363105 creator A5084461397 @default.
- W2579363105 date "2016-12-01" @default.
- W2579363105 modified "2023-09-26" @default.
- W2579363105 title "An analog neural network that learns Sudoku-like puzzle rules" @default.
- W2579363105 cites W1695065985 @default.
- W2579363105 cites W1969071827 @default.
- W2579363105 cites W2092001091 @default.
- W2579363105 cites W2093695923 @default.
- W2579363105 cites W2117723874 @default.
- W2579363105 cites W2185242414 @default.
- W2579363105 doi "https://doi.org/10.1109/ftc.2016.7821701" @default.
- W2579363105 hasPublicationYear "2016" @default.
- W2579363105 type Work @default.
- W2579363105 sameAs 2579363105 @default.
- W2579363105 citedByCount "4" @default.
- W2579363105 countsByYear W25793631052019 @default.
- W2579363105 countsByYear W25793631052020 @default.
- W2579363105 crossrefType "proceedings-article" @default.
- W2579363105 hasAuthorship W2579363105A5076860381 @default.
- W2579363105 hasAuthorship W2579363105A5084461397 @default.
- W2579363105 hasConcept C154945302 @default.
- W2579363105 hasConcept C41008148 @default.
- W2579363105 hasConcept C50644808 @default.
- W2579363105 hasConceptScore W2579363105C154945302 @default.
- W2579363105 hasConceptScore W2579363105C41008148 @default.
- W2579363105 hasConceptScore W2579363105C50644808 @default.
- W2579363105 hasLocation W25793631051 @default.
- W2579363105 hasOpenAccess W2579363105 @default.
- W2579363105 hasPrimaryLocation W25793631051 @default.
- W2579363105 hasRelatedWork W2159443810 @default.
- W2579363105 hasRelatedWork W2358668433 @default.
- W2579363105 hasRelatedWork W2386387936 @default.
- W2579363105 hasRelatedWork W2390279801 @default.
- W2579363105 hasRelatedWork W2748952813 @default.
- W2579363105 hasRelatedWork W2899084033 @default.
- W2579363105 hasRelatedWork W3001020386 @default.
- W2579363105 hasRelatedWork W3107474891 @default.
- W2579363105 hasRelatedWork W644753246 @default.
- W2579363105 hasRelatedWork W1629725936 @default.
- W2579363105 isParatext "false" @default.
- W2579363105 isRetracted "false" @default.
- W2579363105 magId "2579363105" @default.
- W2579363105 workType "article" @default.