Matches in SemOpenAlex for { <https://semopenalex.org/work/W2045491133> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2045491133 abstract "Artificial neural networks can potentially control autonomous robots, vehicles, factories, or game players more robustly than traditional approaches. Neuroevolution, i.e. the artificial evolution of neural networks, is a method for finding the right topology and connection weights to specify the desired control behavior. The challenge for neuroevolution is that difficult tasks may require complex networks with many connections, all of which must be set to the right values. Even if a network exists that can solve the task, evolution may not be able to find it in such a high-dimensional search space. This dissertation presents the NeuroEvolution of Augmenting Topologies (NEAT) method, which makes search for complex solutions feasible. In a process called complexification, NEAT begins by searching in a space of simple networks, and gradually makes them more complex as the search progresses. By starting minimally, NEAT is more likely to find efficient and robust solutions than neuroevolution methods that begin with large fixed or randomized topologies; by elaborating on existing solutions, it can gradually construct even highly complex solutions. In this dissertation, NEAT is first shown faster than traditional approaches on a challenging reinforcement learning benchmark task. Second, by building on existing structure, it is shown to maintain an “arms race” even in open-ended coevolution. Third, NEAT is used to successfully discover complex behavior in three challenging domains: the game of Go, an automobile warning system, and a real-time interactive video game. Experimental results in these domains demonstrate that NEAT makes entirely new applications of machine learning possible." @default.
- W2045491133 created "2016-06-24" @default.
- W2045491133 creator A5020441009 @default.
- W2045491133 creator A5029264794 @default.
- W2045491133 date "2004-01-01" @default.
- W2045491133 modified "2023-10-16" @default.
- W2045491133 title "Efficient evolution of neural networks through complexification" @default.
- W2045491133 hasPublicationYear "2004" @default.
- W2045491133 type Work @default.
- W2045491133 sameAs 2045491133 @default.
- W2045491133 citedByCount "73" @default.
- W2045491133 countsByYear W20454911332012 @default.
- W2045491133 countsByYear W20454911332013 @default.
- W2045491133 countsByYear W20454911332014 @default.
- W2045491133 countsByYear W20454911332015 @default.
- W2045491133 countsByYear W20454911332018 @default.
- W2045491133 countsByYear W20454911332019 @default.
- W2045491133 countsByYear W20454911332020 @default.
- W2045491133 countsByYear W20454911332021 @default.
- W2045491133 crossrefType "dissertation" @default.
- W2045491133 hasAuthorship W2045491133A5020441009 @default.
- W2045491133 hasAuthorship W2045491133A5029264794 @default.
- W2045491133 hasConcept C111919701 @default.
- W2045491133 hasConcept C118070581 @default.
- W2045491133 hasConcept C119857082 @default.
- W2045491133 hasConcept C13280743 @default.
- W2045491133 hasConcept C134306372 @default.
- W2045491133 hasConcept C154945302 @default.
- W2045491133 hasConcept C185798385 @default.
- W2045491133 hasConcept C199360897 @default.
- W2045491133 hasConcept C199845137 @default.
- W2045491133 hasConcept C205649164 @default.
- W2045491133 hasConcept C2777103148 @default.
- W2045491133 hasConcept C2780801425 @default.
- W2045491133 hasConcept C33923547 @default.
- W2045491133 hasConcept C41008148 @default.
- W2045491133 hasConcept C50644808 @default.
- W2045491133 hasConcept C97541855 @default.
- W2045491133 hasConceptScore W2045491133C111919701 @default.
- W2045491133 hasConceptScore W2045491133C118070581 @default.
- W2045491133 hasConceptScore W2045491133C119857082 @default.
- W2045491133 hasConceptScore W2045491133C13280743 @default.
- W2045491133 hasConceptScore W2045491133C134306372 @default.
- W2045491133 hasConceptScore W2045491133C154945302 @default.
- W2045491133 hasConceptScore W2045491133C185798385 @default.
- W2045491133 hasConceptScore W2045491133C199360897 @default.
- W2045491133 hasConceptScore W2045491133C199845137 @default.
- W2045491133 hasConceptScore W2045491133C205649164 @default.
- W2045491133 hasConceptScore W2045491133C2777103148 @default.
- W2045491133 hasConceptScore W2045491133C2780801425 @default.
- W2045491133 hasConceptScore W2045491133C33923547 @default.
- W2045491133 hasConceptScore W2045491133C41008148 @default.
- W2045491133 hasConceptScore W2045491133C50644808 @default.
- W2045491133 hasConceptScore W2045491133C97541855 @default.
- W2045491133 hasLocation W20454911331 @default.
- W2045491133 hasOpenAccess W2045491133 @default.
- W2045491133 hasPrimaryLocation W20454911331 @default.
- W2045491133 hasRelatedWork W1547737196 @default.
- W2045491133 hasRelatedWork W1548589545 @default.
- W2045491133 hasRelatedWork W2076329865 @default.
- W2045491133 hasRelatedWork W2100097207 @default.
- W2045491133 hasRelatedWork W2100211715 @default.
- W2045491133 hasRelatedWork W2111935653 @default.
- W2045491133 hasRelatedWork W2112036188 @default.
- W2045491133 hasRelatedWork W2116850952 @default.
- W2045491133 hasRelatedWork W2119814172 @default.
- W2045491133 hasRelatedWork W2121863487 @default.
- W2045491133 hasRelatedWork W2124290836 @default.
- W2045491133 hasRelatedWork W2138784882 @default.
- W2045491133 hasRelatedWork W2140685838 @default.
- W2045491133 hasRelatedWork W2144357723 @default.
- W2045491133 hasRelatedWork W2147147005 @default.
- W2045491133 hasRelatedWork W2148067905 @default.
- W2045491133 hasRelatedWork W2153684665 @default.
- W2045491133 hasRelatedWork W2162813238 @default.
- W2045491133 hasRelatedWork W2169803171 @default.
- W2045491133 hasRelatedWork W2171658832 @default.
- W2045491133 isParatext "false" @default.
- W2045491133 isRetracted "false" @default.
- W2045491133 magId "2045491133" @default.
- W2045491133 workType "dissertation" @default.