Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015549998> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3015549998 endingPage "641" @default.
- W3015549998 startingPage "626" @default.
- W3015549998 abstract "Hand-crafting effective and efficient structures for recurrent neural networks (RNNs) is a difficult, expensive, and time-consuming process. To address this challenge, we propose a novel neuro-evolution algorithm based on ant colony optimization (ACO), called Ant-based Neural Topology Search (ANTS), for directly optimizing RNN topologies. The procedure selects from multiple modern recurrent cell types such as (varDelta )-RNN, GRU, LSTM, MGU and UGRNN cells, as well as recurrent connections which may span multiple layers and/or steps of time. In order to introduce an inductive bias that encourages the formation of sparser synaptic connectivity patterns, we investigate several variations of the core algorithm. We do so primarily by formulating different functions that drive the underlying pheromone simulation process (which mimic L1 and L2 regularization in standard machine learning) as well as by introducing ant agents with specialized roles (inspired by how real ant colonies operate), i.e., explorer ants that construct the initial feed forward structure and social ants which select nodes from the feed forward connections to subsequently craft recurrent memory structures. We also incorporate communal intelligence, where best weights are shared by the ant colony for weight initialization, reducing the number of backpropagation epochs required to locally train candidate RNNs, speeding up the neuro-evolution process. Our results demonstrate that the sparser RNNs evolved by ANTS significantly outperform traditional one and two layer architectures consisting of modern memory cells, as well as the well-known NEAT algorithm. Furthermore, we improve upon prior state-of-the-art results on the time series dataset utilized in our experiments." @default.
- W3015549998 created "2020-04-17" @default.
- W3015549998 creator A5013804148 @default.
- W3015549998 creator A5065630093 @default.
- W3015549998 creator A5084332360 @default.
- W3015549998 date "2020-01-01" @default.
- W3015549998 modified "2023-09-25" @default.
- W3015549998 title "Ant-based Neural Topology Search (ANTS) for Optimizing Recurrent Networks" @default.
- W3015549998 cites W1659842140 @default.
- W3015549998 cites W1975586526 @default.
- W3015549998 cites W1980522774 @default.
- W3015549998 cites W2064675550 @default.
- W3015549998 cites W2095878602 @default.
- W3015549998 cites W2110485445 @default.
- W3015549998 cites W2111935653 @default.
- W3015549998 cites W2119814172 @default.
- W3015549998 cites W2134514463 @default.
- W3015549998 cites W2171928131 @default.
- W3015549998 cites W2319453305 @default.
- W3015549998 cites W2593744649 @default.
- W3015549998 cites W2604228884 @default.
- W3015549998 cites W2751148689 @default.
- W3015549998 cites W2810074991 @default.
- W3015549998 cites W2939520374 @default.
- W3015549998 cites W2963029020 @default.
- W3015549998 cites W2963365220 @default.
- W3015549998 cites W2963500514 @default.
- W3015549998 cites W4255158661 @default.
- W3015549998 cites W836056349 @default.
- W3015549998 doi "https://doi.org/10.1007/978-3-030-43722-0_40" @default.
- W3015549998 hasPublicationYear "2020" @default.
- W3015549998 type Work @default.
- W3015549998 sameAs 3015549998 @default.
- W3015549998 citedByCount "5" @default.
- W3015549998 countsByYear W30155499982020 @default.
- W3015549998 countsByYear W30155499982021 @default.
- W3015549998 crossrefType "book-chapter" @default.
- W3015549998 hasAuthorship W3015549998A5013804148 @default.
- W3015549998 hasAuthorship W3015549998A5065630093 @default.
- W3015549998 hasAuthorship W3015549998A5084332360 @default.
- W3015549998 hasBestOaLocation W30155499982 @default.
- W3015549998 hasConcept C111919701 @default.
- W3015549998 hasConcept C114466953 @default.
- W3015549998 hasConcept C119857082 @default.
- W3015549998 hasConcept C147168706 @default.
- W3015549998 hasConcept C154945302 @default.
- W3015549998 hasConcept C199360897 @default.
- W3015549998 hasConcept C199845137 @default.
- W3015549998 hasConcept C40128228 @default.
- W3015549998 hasConcept C41008148 @default.
- W3015549998 hasConcept C50644808 @default.
- W3015549998 hasConcept C60891933 @default.
- W3015549998 hasConcept C66949984 @default.
- W3015549998 hasConceptScore W3015549998C111919701 @default.
- W3015549998 hasConceptScore W3015549998C114466953 @default.
- W3015549998 hasConceptScore W3015549998C119857082 @default.
- W3015549998 hasConceptScore W3015549998C147168706 @default.
- W3015549998 hasConceptScore W3015549998C154945302 @default.
- W3015549998 hasConceptScore W3015549998C199360897 @default.
- W3015549998 hasConceptScore W3015549998C199845137 @default.
- W3015549998 hasConceptScore W3015549998C40128228 @default.
- W3015549998 hasConceptScore W3015549998C41008148 @default.
- W3015549998 hasConceptScore W3015549998C50644808 @default.
- W3015549998 hasConceptScore W3015549998C60891933 @default.
- W3015549998 hasConceptScore W3015549998C66949984 @default.
- W3015549998 hasLocation W30155499981 @default.
- W3015549998 hasLocation W30155499982 @default.
- W3015549998 hasOpenAccess W3015549998 @default.
- W3015549998 hasPrimaryLocation W30155499981 @default.
- W3015549998 hasRelatedWork W10877471 @default.
- W3015549998 hasRelatedWork W11934588 @default.
- W3015549998 hasRelatedWork W12251780 @default.
- W3015549998 hasRelatedWork W13678974 @default.
- W3015549998 hasRelatedWork W2235786 @default.
- W3015549998 hasRelatedWork W2683128 @default.
- W3015549998 hasRelatedWork W7339520 @default.
- W3015549998 hasRelatedWork W8821115 @default.
- W3015549998 hasRelatedWork W9321062 @default.
- W3015549998 hasRelatedWork W2217443 @default.
- W3015549998 isParatext "false" @default.
- W3015549998 isRetracted "false" @default.
- W3015549998 magId "3015549998" @default.
- W3015549998 workType "book-chapter" @default.