Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201060963> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3201060963 endingPage "506" @default.
- W3201060963 startingPage "496" @default.
- W3201060963 abstract "Spiking neural networks (SNNs) aim to replicate energy efficiency, learning speed and temporal processing of biological brains. However, accuracy and learning speed of such networks is still behind reinforcement learning (RL) models based on traditional neural models. This work combines a pre-trained binary convolutional neural network with an SNN trained online through reward-modulated STDP in order to leverage advantages of both models. The spiking network is an extension of its previous version, with improvements in architecture and dynamics to address a more challenging task. We focus on extensive experimental evaluation of the proposed model with optimized state-of-the-art baselines, namely proximal policy optimization (PPO) and deep Q network (DQN). The models are compared on a grid-world environment with high dimensional observations, consisting of RGB images with up to 256 × 256 pixels. The experimental results show that the proposed architecture can be a competitive alternative to deep reinforcement learning (DRL) in the evaluated environment and provide a foundation for more complex future applications of spiking networks." @default.
- W3201060963 created "2021-09-27" @default.
- W3201060963 creator A5010179490 @default.
- W3201060963 creator A5025550530 @default.
- W3201060963 date "2021-12-01" @default.
- W3201060963 modified "2023-10-17" @default.
- W3201060963 title "Combining STDP and binary networks for reinforcement learning from images and sparse rewards" @default.
- W3201060963 cites W1738827650 @default.
- W3201060963 cites W2020539709 @default.
- W3201060963 cites W2027443147 @default.
- W3201060963 cites W2052788949 @default.
- W3201060963 cites W2098192620 @default.
- W3201060963 cites W2126404188 @default.
- W3201060963 cites W2138214290 @default.
- W3201060963 cites W2145339207 @default.
- W3201060963 cites W2271476098 @default.
- W3201060963 cites W2746553466 @default.
- W3201060963 cites W2754052872 @default.
- W3201060963 cites W2795738670 @default.
- W3201060963 cites W2807894615 @default.
- W3201060963 cites W2900163261 @default.
- W3201060963 cites W2922002199 @default.
- W3201060963 cites W2944119451 @default.
- W3201060963 cites W2949676527 @default.
- W3201060963 cites W2960575309 @default.
- W3201060963 cites W2964010909 @default.
- W3201060963 cites W2990747716 @default.
- W3201060963 cites W3036016986 @default.
- W3201060963 cites W3041202696 @default.
- W3201060963 cites W3043133474 @default.
- W3201060963 cites W3100718033 @default.
- W3201060963 cites W3105516366 @default.
- W3201060963 cites W4242770316 @default.
- W3201060963 doi "https://doi.org/10.1016/j.neunet.2021.09.010" @default.
- W3201060963 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34601362" @default.
- W3201060963 hasPublicationYear "2021" @default.
- W3201060963 type Work @default.
- W3201060963 sameAs 3201060963 @default.
- W3201060963 citedByCount "5" @default.
- W3201060963 countsByYear W32010609632022 @default.
- W3201060963 countsByYear W32010609632023 @default.
- W3201060963 crossrefType "journal-article" @default.
- W3201060963 hasAuthorship W3201060963A5010179490 @default.
- W3201060963 hasAuthorship W3201060963A5025550530 @default.
- W3201060963 hasConcept C108583219 @default.
- W3201060963 hasConcept C11731999 @default.
- W3201060963 hasConcept C119857082 @default.
- W3201060963 hasConcept C153083717 @default.
- W3201060963 hasConcept C154945302 @default.
- W3201060963 hasConcept C33923547 @default.
- W3201060963 hasConcept C41008148 @default.
- W3201060963 hasConcept C48372109 @default.
- W3201060963 hasConcept C50644808 @default.
- W3201060963 hasConcept C81363708 @default.
- W3201060963 hasConcept C94375191 @default.
- W3201060963 hasConcept C97541855 @default.
- W3201060963 hasConceptScore W3201060963C108583219 @default.
- W3201060963 hasConceptScore W3201060963C11731999 @default.
- W3201060963 hasConceptScore W3201060963C119857082 @default.
- W3201060963 hasConceptScore W3201060963C153083717 @default.
- W3201060963 hasConceptScore W3201060963C154945302 @default.
- W3201060963 hasConceptScore W3201060963C33923547 @default.
- W3201060963 hasConceptScore W3201060963C41008148 @default.
- W3201060963 hasConceptScore W3201060963C48372109 @default.
- W3201060963 hasConceptScore W3201060963C50644808 @default.
- W3201060963 hasConceptScore W3201060963C81363708 @default.
- W3201060963 hasConceptScore W3201060963C94375191 @default.
- W3201060963 hasConceptScore W3201060963C97541855 @default.
- W3201060963 hasFunder F4320321091 @default.
- W3201060963 hasFunder F4320322025 @default.
- W3201060963 hasFunder F4320323678 @default.
- W3201060963 hasLocation W32010609631 @default.
- W3201060963 hasLocation W32010609632 @default.
- W3201060963 hasOpenAccess W3201060963 @default.
- W3201060963 hasPrimaryLocation W32010609631 @default.
- W3201060963 hasRelatedWork W2337926734 @default.
- W3201060963 hasRelatedWork W2731899572 @default.
- W3201060963 hasRelatedWork W2963958939 @default.
- W3201060963 hasRelatedWork W3133861977 @default.
- W3201060963 hasRelatedWork W3173182854 @default.
- W3201060963 hasRelatedWork W4311257506 @default.
- W3201060963 hasRelatedWork W4312417841 @default.
- W3201060963 hasRelatedWork W4320802194 @default.
- W3201060963 hasRelatedWork W4321369474 @default.
- W3201060963 hasRelatedWork W4366224123 @default.
- W3201060963 hasVolume "144" @default.
- W3201060963 isParatext "false" @default.
- W3201060963 isRetracted "false" @default.
- W3201060963 magId "3201060963" @default.
- W3201060963 workType "article" @default.