Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090174963> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W3090174963 abstract "Biological brains still far exceed artificial intelligence systems, both in terms of control capabilities and power consumption. Spiking neural networks (SNNs) are a promising model, inspired by neuroscience and functionally closer to the way neurons process information. While recent advancements in neuromorphic hardware allow energy efficient synthesis of spiking networks, the training of such networks remains an open problem. In this work we focus on reinforcement learning with sparse and delayed rewards. The proposed architecture has four distinct layers and addresses the limitation of previous models in terms of scalability with input dimensions. Our SNN is evaluated on classical reinforcement learning and control tasks and is compared to two common RL algorithms: Q-learning and deep Q-network (DQN). Experiments demonstrate that the proposed network outperforms Q-learning on a task with six-dimensional observation space and compares favorably to the evaluated DQN configurations in terms of stability and memory requirements." @default.
- W3090174963 created "2020-10-08" @default.
- W3090174963 creator A5010179490 @default.
- W3090174963 creator A5025550530 @default.
- W3090174963 date "2020-07-01" @default.
- W3090174963 modified "2023-09-25" @default.
- W3090174963 title "Learning from Sparse and Delayed Rewards with a Multilayer Spiking Neural Network" @default.
- W3090174963 cites W1738827650 @default.
- W3090174963 cites W2020539709 @default.
- W3090174963 cites W2027443147 @default.
- W3090174963 cites W2052788949 @default.
- W3090174963 cites W2101967150 @default.
- W3090174963 cites W2111935653 @default.
- W3090174963 cites W2126404188 @default.
- W3090174963 cites W2145339207 @default.
- W3090174963 cites W2271476098 @default.
- W3090174963 cites W2283674326 @default.
- W3090174963 cites W2570285138 @default.
- W3090174963 cites W2730274928 @default.
- W3090174963 cites W2754052872 @default.
- W3090174963 cites W2807894615 @default.
- W3090174963 cites W2890344110 @default.
- W3090174963 cites W2900163261 @default.
- W3090174963 cites W2911087563 @default.
- W3090174963 cites W2922002199 @default.
- W3090174963 cites W2944119451 @default.
- W3090174963 cites W2951396559 @default.
- W3090174963 cites W2964010909 @default.
- W3090174963 cites W2968865419 @default.
- W3090174963 cites W2980764939 @default.
- W3090174963 cites W3041202696 @default.
- W3090174963 cites W3103266921 @default.
- W3090174963 cites W4214548942 @default.
- W3090174963 cites W4242770316 @default.
- W3090174963 doi "https://doi.org/10.1109/ijcnn48605.2020.9206846" @default.
- W3090174963 hasPublicationYear "2020" @default.
- W3090174963 type Work @default.
- W3090174963 sameAs 3090174963 @default.
- W3090174963 citedByCount "2" @default.
- W3090174963 countsByYear W30901749632022 @default.
- W3090174963 countsByYear W30901749632023 @default.
- W3090174963 crossrefType "proceedings-article" @default.
- W3090174963 hasAuthorship W3090174963A5010179490 @default.
- W3090174963 hasAuthorship W3090174963A5025550530 @default.
- W3090174963 hasConcept C11731999 @default.
- W3090174963 hasConcept C119857082 @default.
- W3090174963 hasConcept C153180895 @default.
- W3090174963 hasConcept C154945302 @default.
- W3090174963 hasConcept C41008148 @default.
- W3090174963 hasConcept C50644808 @default.
- W3090174963 hasConceptScore W3090174963C11731999 @default.
- W3090174963 hasConceptScore W3090174963C119857082 @default.
- W3090174963 hasConceptScore W3090174963C153180895 @default.
- W3090174963 hasConceptScore W3090174963C154945302 @default.
- W3090174963 hasConceptScore W3090174963C41008148 @default.
- W3090174963 hasConceptScore W3090174963C50644808 @default.
- W3090174963 hasLocation W30901749631 @default.
- W3090174963 hasOpenAccess W3090174963 @default.
- W3090174963 hasPrimaryLocation W30901749631 @default.
- W3090174963 hasRelatedWork W2003715592 @default.
- W3090174963 hasRelatedWork W2885843018 @default.
- W3090174963 hasRelatedWork W2961085424 @default.
- W3090174963 hasRelatedWork W3046775127 @default.
- W3090174963 hasRelatedWork W4205958290 @default.
- W3090174963 hasRelatedWork W4286629047 @default.
- W3090174963 hasRelatedWork W4306321456 @default.
- W3090174963 hasRelatedWork W4306674287 @default.
- W3090174963 hasRelatedWork W1629725936 @default.
- W3090174963 hasRelatedWork W4224009465 @default.
- W3090174963 isParatext "false" @default.
- W3090174963 isRetracted "false" @default.
- W3090174963 magId "3090174963" @default.
- W3090174963 workType "article" @default.