Matches in SemOpenAlex for { <https://semopenalex.org/work/W2512546963> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2512546963 abstract "There has been significant recent interest towards achieving highly efficient deep neural network architectures. A promising paradigm for achieving this is the concept of evolutionary deep intelligence, which attempts to mimic biological evolution processes to synthesize highly-efficient deep neural networks over successive generations. An important aspect of evolutionary deep intelligence is the genetic encoding scheme used to mimic heredity, which can have a significant impact on the quality of offspring deep neural networks. Motivated by the neurobiological phenomenon of synaptic clustering, we introduce a new genetic encoding scheme where synaptic probability is driven towards the formation of a highly sparse set of synaptic clusters. Experimental results for the task of image classification demonstrated that the synthesized offspring networks using this synaptic cluster-driven genetic encoding scheme can achieve state-of-the-art performance while having network architectures that are not only significantly more efficient (with a ~125-fold decrease in synapses for MNIST) compared to the original ancestor network, but also tailored for GPU-accelerated machine learning applications." @default.
- W2512546963 created "2016-09-16" @default.
- W2512546963 creator A5034161060 @default.
- W2512546963 creator A5040284711 @default.
- W2512546963 date "2016-09-06" @default.
- W2512546963 modified "2023-09-27" @default.
- W2512546963 title "Evolutionary Synthesis of Deep Neural Networks via Synaptic Cluster-driven Genetic Encoding" @default.
- W2512546963 cites W1724438581 @default.
- W2512546963 cites W1903029394 @default.
- W2512546963 cites W1935978687 @default.
- W2512546963 cites W1965154800 @default.
- W2512546963 cites W1966931935 @default.
- W2512546963 cites W2019251983 @default.
- W2512546963 cites W2019523818 @default.
- W2512546963 cites W2022508996 @default.
- W2512546963 cites W2065188691 @default.
- W2512546963 cites W2097117768 @default.
- W2512546963 cites W2111077768 @default.
- W2512546963 cites W2112739286 @default.
- W2512546963 cites W2112796928 @default.
- W2512546963 cites W2114766824 @default.
- W2512546963 cites W2119144962 @default.
- W2512546963 cites W2160815625 @default.
- W2512546963 cites W2179596243 @default.
- W2512546963 cites W2201721810 @default.
- W2512546963 cites W2325939864 @default.
- W2512546963 cites W2342840547 @default.
- W2512546963 cites W2423540713 @default.
- W2512546963 cites W2465934950 @default.
- W2512546963 cites W2468368736 @default.
- W2512546963 cites W2475287302 @default.
- W2512546963 cites W2513419314 @default.
- W2512546963 cites W2905110430 @default.
- W2512546963 cites W2950967261 @default.
- W2512546963 cites W2952432176 @default.
- W2512546963 cites W2953066166 @default.
- W2512546963 cites W2953203558 @default.
- W2512546963 cites W2963674932 @default.
- W2512546963 cites W3118608800 @default.
- W2512546963 cites W92617545 @default.
- W2512546963 hasPublicationYear "2016" @default.
- W2512546963 type Work @default.
- W2512546963 sameAs 2512546963 @default.
- W2512546963 citedByCount "16" @default.
- W2512546963 countsByYear W25125469632017 @default.
- W2512546963 countsByYear W25125469632018 @default.
- W2512546963 countsByYear W25125469632019 @default.
- W2512546963 crossrefType "posted-content" @default.
- W2512546963 hasAuthorship W2512546963A5034161060 @default.
- W2512546963 hasAuthorship W2512546963A5040284711 @default.
- W2512546963 hasConcept C108583219 @default.
- W2512546963 hasConcept C11731999 @default.
- W2512546963 hasConcept C119857082 @default.
- W2512546963 hasConcept C125411270 @default.
- W2512546963 hasConcept C154945302 @default.
- W2512546963 hasConcept C190502265 @default.
- W2512546963 hasConcept C41008148 @default.
- W2512546963 hasConcept C50644808 @default.
- W2512546963 hasConcept C73555534 @default.
- W2512546963 hasConceptScore W2512546963C108583219 @default.
- W2512546963 hasConceptScore W2512546963C11731999 @default.
- W2512546963 hasConceptScore W2512546963C119857082 @default.
- W2512546963 hasConceptScore W2512546963C125411270 @default.
- W2512546963 hasConceptScore W2512546963C154945302 @default.
- W2512546963 hasConceptScore W2512546963C190502265 @default.
- W2512546963 hasConceptScore W2512546963C41008148 @default.
- W2512546963 hasConceptScore W2512546963C50644808 @default.
- W2512546963 hasConceptScore W2512546963C73555534 @default.
- W2512546963 hasLocation W25125469631 @default.
- W2512546963 hasOpenAccess W2512546963 @default.
- W2512546963 hasPrimaryLocation W25125469631 @default.
- W2512546963 hasRelatedWork W1508604245 @default.
- W2512546963 hasRelatedWork W1573687737 @default.
- W2512546963 hasRelatedWork W1686810756 @default.
- W2512546963 hasRelatedWork W1724438581 @default.
- W2512546963 hasRelatedWork W2072128103 @default.
- W2512546963 hasRelatedWork W2111935653 @default.
- W2512546963 hasRelatedWork W2112796928 @default.
- W2512546963 hasRelatedWork W2114766824 @default.
- W2512546963 hasRelatedWork W2138784882 @default.
- W2512546963 hasRelatedWork W2140685838 @default.
- W2512546963 hasRelatedWork W2143612262 @default.
- W2512546963 hasRelatedWork W2163605009 @default.
- W2512546963 hasRelatedWork W2606844113 @default.
- W2512546963 hasRelatedWork W2770656417 @default.
- W2512546963 hasRelatedWork W2771070736 @default.
- W2512546963 hasRelatedWork W2919115771 @default.
- W2512546963 hasRelatedWork W2950967261 @default.
- W2512546963 hasRelatedWork W2952432176 @default.
- W2512546963 hasRelatedWork W2964232044 @default.
- W2512546963 hasRelatedWork W3118608800 @default.
- W2512546963 isParatext "false" @default.
- W2512546963 isRetracted "false" @default.
- W2512546963 magId "2512546963" @default.
- W2512546963 workType "article" @default.