FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022582119> ?p ?o ?g. }

• W3022582119 abstract "Artificially intelligent machines have to explore their environment, store information about it, and use this information to improve future decision making. As such, the quest is to either provide these systems with internal models about their environment or to imbue machines with the ability to create their own models—ideally the later. These models are mental representations of the environment, and we have previously shown that neuroevolution is a powerful method to create artificially intelligent machines (also referred to as agents) that can form said representations. Furthermore, we have shown that one can quantify representations and use that quantity to augment the performance of a genetic algorithm. Instead of just optimizing for performance, one can also positively select for agents that have better representations. The neuroevolutionary approach, that improves performance and lets these agents develop representations, works well for Markov Brains, which are a form of Cartesian Genetic Programming network. Conventional artificial neural networks and their recurrent counterparts, RNNs and LSTMs, are however primarily trained by backpropagation and not evolved, and they behave differently with respect to their ability to form representations. When evolved, RNNs and LSTMs do not form sparse and distinct representations, they “smear” the information about individual concepts of the environment over all nodes in the system. This ultimately makes these systems more brittle and less capable. The question we seek to address, now, is how can we create systems that evolve to have meaningful representations while preventing them from smearing these representations? We look at genetic programming trees as an interesting computational paradigm, as they can take a lot of information in through their various leaves, but at the same time condense that computation into a single node in the end. We hypothesize that this computational condensation could also prevent the smearing of information. Here, we explore how these tree structures evolve and form representations, and we test to what degree these systems either “smear” or condense information." @default.
• W3022582119 created "2020-05-13" @default.
• W3022582119 creator A5022052672 @default.
• W3022582119 creator A5029972705 @default.
• W3022582119 date "2020-01-01" @default.
• W3022582119 modified "2023-09-26" @default.
• W3022582119 title "The Evolution of Representations in Genetic Programming Trees" @default.
• W3022582119 cites W2009219975 @default.
• W3022582119 cites W2020320008 @default.
• W3022582119 cites W2022029210 @default.
• W3022582119 cites W2040492000 @default.
• W3022582119 cites W2057268277 @default.
• W3022582119 cites W2064675550 @default.
• W3022582119 cites W2065038230 @default.
• W3022582119 cites W2111935653 @default.
• W3022582119 cites W2124290836 @default.
• W3022582119 cites W2129578597 @default.
• W3022582119 cites W2136414484 @default.
• W3022582119 cites W2166110729 @default.
• W3022582119 cites W2171658832 @default.
• W3022582119 cites W2397253692 @default.
• W3022582119 cites W2807456360 @default.
• W3022582119 cites W2906697496 @default.
• W3022582119 cites W2963128810 @default.
• W3022582119 cites W3100183562 @default.
• W3022582119 cites W4213333889 @default.
• W3022582119 cites W4238753141 @default.
• W3022582119 cites W4256674099 @default.
• W3022582119 cites W2963753658 @default.
• W3022582119 doi "https://doi.org/10.1007/978-3-030-39958-0_7" @default.
• W3022582119 hasPublicationYear "2020" @default.
• W3022582119 type Work @default.
• W3022582119 sameAs 3022582119 @default.
• W3022582119 citedByCount "1" @default.
• W3022582119 countsByYear W30225821192021 @default.
• W3022582119 crossrefType "book-chapter" @default.
• W3022582119 hasAuthorship W3022582119A5022052672 @default.
• W3022582119 hasAuthorship W3022582119A5029972705 @default.
• W3022582119 hasConcept C110332635 @default.
• W3022582119 hasConcept C118070581 @default.
• W3022582119 hasConcept C119857082 @default.
• W3022582119 hasConcept C147168706 @default.
• W3022582119 hasConcept C154945302 @default.
• W3022582119 hasConcept C19273510 @default.
• W3022582119 hasConcept C41008148 @default.
• W3022582119 hasConcept C50644808 @default.
• W3022582119 hasConcept C80444323 @default.
• W3022582119 hasConcept C8880873 @default.
• W3022582119 hasConceptScore W3022582119C110332635 @default.
• W3022582119 hasConceptScore W3022582119C118070581 @default.
• W3022582119 hasConceptScore W3022582119C119857082 @default.
• W3022582119 hasConceptScore W3022582119C147168706 @default.
• W3022582119 hasConceptScore W3022582119C154945302 @default.
• W3022582119 hasConceptScore W3022582119C19273510 @default.
• W3022582119 hasConceptScore W3022582119C41008148 @default.
• W3022582119 hasConceptScore W3022582119C50644808 @default.
• W3022582119 hasConceptScore W3022582119C80444323 @default.
• W3022582119 hasConceptScore W3022582119C8880873 @default.
• W3022582119 hasLocation W30225821191 @default.
• W3022582119 hasOpenAccess W3022582119 @default.
• W3022582119 hasPrimaryLocation W30225821191 @default.
• W3022582119 hasRelatedWork W1075976 @default.
• W3022582119 hasRelatedWork W12508877 @default.
• W3022582119 hasRelatedWork W12582432 @default.
• W3022582119 hasRelatedWork W13211703 @default.
• W3022582119 hasRelatedWork W13420288 @default.
• W3022582119 hasRelatedWork W13678974 @default.
• W3022582119 hasRelatedWork W15164554 @default.
• W3022582119 hasRelatedWork W1562032 @default.
• W3022582119 hasRelatedWork W2683128 @default.
• W3022582119 hasRelatedWork W8897532 @default.
• W3022582119 isParatext "false" @default.
• W3022582119 isRetracted "false" @default.
• W3022582119 magId "3022582119" @default.
• W3022582119 workType "book-chapter" @default.