Matches in SemOpenAlex for { <https://semopenalex.org/work/W3023212902> ?p ?o ?g. }
- W3023212902 endingPage "32" @default.
- W3023212902 startingPage "14" @default.
- W3023212902 abstract "In neural networks literature, there is a strong interest in identifying and defining activation functions which can improve neural network performance. In recent years there has been a renovated interest of the scientific community in investigating activation functions which can be trained during the learning process, usually referred to as trainable, learnable or adaptable activation functions. They appear to lead to better network performance. Diverse and heterogeneous models of trainable activation function have been proposed in the literature. In this paper, we present a survey of these models. Starting from a discussion on the use of the term activation function in literature, we propose a taxonomy of trainable activation functions, highlight common and distinctive proprieties of recent and past models, and discuss main advantages and limitations of this type of approach. We show that many of the proposed approaches are equivalent to adding neuron layers which use fixed (non-trainable) activation functions and some simple local rule that constraints the corresponding weight layers." @default.
- W3023212902 created "2020-05-13" @default.
- W3023212902 creator A5032731543 @default.
- W3023212902 creator A5048689229 @default.
- W3023212902 creator A5059881379 @default.
- W3023212902 creator A5089890021 @default.
- W3023212902 date "2021-06-01" @default.
- W3023212902 modified "2023-10-17" @default.
- W3023212902 title "A survey on modern trainable activation functions" @default.
- W3023212902 cites W139921695 @default.
- W3023212902 cites W1677182931 @default.
- W3023212902 cites W1982845960 @default.
- W3023212902 cites W2011743708 @default.
- W3023212902 cites W2012667922 @default.
- W3023212902 cites W2027945811 @default.
- W3023212902 cites W2029654180 @default.
- W3023212902 cites W2043562021 @default.
- W3023212902 cites W2093503827 @default.
- W3023212902 cites W2097117768 @default.
- W3023212902 cites W2098290011 @default.
- W3023212902 cites W2103496339 @default.
- W3023212902 cites W2107878631 @default.
- W3023212902 cites W2112796928 @default.
- W3023212902 cites W2116424792 @default.
- W3023212902 cites W2117539524 @default.
- W3023212902 cites W2119169819 @default.
- W3023212902 cites W2125621954 @default.
- W3023212902 cites W2137234026 @default.
- W3023212902 cites W2137983211 @default.
- W3023212902 cites W2153796359 @default.
- W3023212902 cites W2155399784 @default.
- W3023212902 cites W2158581396 @default.
- W3023212902 cites W2160915159 @default.
- W3023212902 cites W2270144854 @default.
- W3023212902 cites W2307425316 @default.
- W3023212902 cites W2336829316 @default.
- W3023212902 cites W2730411900 @default.
- W3023212902 cites W2753772327 @default.
- W3023212902 cites W2792268997 @default.
- W3023212902 cites W2920039561 @default.
- W3023212902 cites W2956698489 @default.
- W3023212902 cites W2962834855 @default.
- W3023212902 cites W2962907613 @default.
- W3023212902 cites W2963273475 @default.
- W3023212902 cites W2963446712 @default.
- W3023212902 cites W3099703817 @default.
- W3023212902 cites W3101806332 @default.
- W3023212902 cites W3125537303 @default.
- W3023212902 doi "https://doi.org/10.1016/j.neunet.2021.01.026" @default.
- W3023212902 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33611065" @default.
- W3023212902 hasPublicationYear "2021" @default.
- W3023212902 type Work @default.
- W3023212902 sameAs 3023212902 @default.
- W3023212902 citedByCount "135" @default.
- W3023212902 countsByYear W30232129022020 @default.
- W3023212902 countsByYear W30232129022021 @default.
- W3023212902 countsByYear W30232129022022 @default.
- W3023212902 countsByYear W30232129022023 @default.
- W3023212902 crossrefType "journal-article" @default.
- W3023212902 hasAuthorship W3023212902A5032731543 @default.
- W3023212902 hasAuthorship W3023212902A5048689229 @default.
- W3023212902 hasAuthorship W3023212902A5059881379 @default.
- W3023212902 hasAuthorship W3023212902A5089890021 @default.
- W3023212902 hasBestOaLocation W30232129022 @default.
- W3023212902 hasConcept C111472728 @default.
- W3023212902 hasConcept C111919701 @default.
- W3023212902 hasConcept C138885662 @default.
- W3023212902 hasConcept C14036430 @default.
- W3023212902 hasConcept C154945302 @default.
- W3023212902 hasConcept C2780586882 @default.
- W3023212902 hasConcept C38365724 @default.
- W3023212902 hasConcept C41008148 @default.
- W3023212902 hasConcept C50644808 @default.
- W3023212902 hasConcept C78458016 @default.
- W3023212902 hasConcept C86803240 @default.
- W3023212902 hasConcept C98045186 @default.
- W3023212902 hasConceptScore W3023212902C111472728 @default.
- W3023212902 hasConceptScore W3023212902C111919701 @default.
- W3023212902 hasConceptScore W3023212902C138885662 @default.
- W3023212902 hasConceptScore W3023212902C14036430 @default.
- W3023212902 hasConceptScore W3023212902C154945302 @default.
- W3023212902 hasConceptScore W3023212902C2780586882 @default.
- W3023212902 hasConceptScore W3023212902C38365724 @default.
- W3023212902 hasConceptScore W3023212902C41008148 @default.
- W3023212902 hasConceptScore W3023212902C50644808 @default.
- W3023212902 hasConceptScore W3023212902C78458016 @default.
- W3023212902 hasConceptScore W3023212902C86803240 @default.
- W3023212902 hasConceptScore W3023212902C98045186 @default.
- W3023212902 hasLocation W30232129021 @default.
- W3023212902 hasLocation W30232129022 @default.
- W3023212902 hasLocation W30232129023 @default.
- W3023212902 hasOpenAccess W3023212902 @default.
- W3023212902 hasPrimaryLocation W30232129021 @default.
- W3023212902 hasRelatedWork W1585007175 @default.
- W3023212902 hasRelatedWork W2898900925 @default.
- W3023212902 hasRelatedWork W3110577345 @default.
- W3023212902 hasRelatedWork W3134817226 @default.
- W3023212902 hasRelatedWork W3137729713 @default.