Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294328372> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4294328372 abstract "I apply recent work on learning to think (2015) and on PowerPlay (2011) to the incremental training of an increasingly general problem solver, continually learning to solve new tasks without forgetting previous skills. The problem solver is a single recurrent neural network (or similar general purpose computer) called ONE. ONE is unusual in the sense that it is trained in various ways, e.g., by black box optimization / reinforcement learning / artificial evolution as well as supervised / unsupervised learning. For example, ONE may learn through neuroevolution to control a robot through environment-changing actions, and learn through unsupervised gradient descent to predict future inputs and vector-valued reward signals as suggested in 1990. User-given tasks can be defined through extra goal-defining input patterns, also proposed in 1990. Suppose ONE has already learned many skills. Now a copy of ONE can be re-trained to learn a new skill, e.g., through neuroevolution without a teacher. Here it may profit from re-using previously learned subroutines, but it may also forget previous skills. Then ONE is retrained in PowerPlay style (2011) on stored input/output traces of (a) ONE's copy executing the new skill and (b) previous instances of ONE whose skills are still considered worth memorizing. Simultaneously, ONE is retrained on old traces (even those of unsuccessful trials) to become a better predictor, without additional expensive interaction with the enviroment. More and more control and prediction skills are thus collapsed into ONE, like in the chunker-automatizer system of the neural history compressor (1991). This forces ONE to relate partially analogous skills (with shared algorithmic information) to each other, creating common subroutines in form of shared subnetworks of ONE, to greatly speed up subsequent learning of additional, novel but algorithmically related skills." @default.
- W4294328372 created "2022-09-02" @default.
- W4294328372 creator A5044629673 @default.
- W4294328372 date "2018-02-24" @default.
- W4294328372 modified "2023-10-04" @default.
- W4294328372 title "One Big Net For Everything" @default.
- W4294328372 doi "https://doi.org/10.48550/arxiv.1802.08864" @default.
- W4294328372 hasPublicationYear "2018" @default.
- W4294328372 type Work @default.
- W4294328372 citedByCount "1" @default.
- W4294328372 countsByYear W42943283722023 @default.
- W4294328372 crossrefType "posted-content" @default.
- W4294328372 hasAuthorship W4294328372A5044629673 @default.
- W4294328372 hasBestOaLocation W42943283721 @default.
- W4294328372 hasConcept C111919701 @default.
- W4294328372 hasConcept C118070581 @default.
- W4294328372 hasConcept C119857082 @default.
- W4294328372 hasConcept C138885662 @default.
- W4294328372 hasConcept C145420912 @default.
- W4294328372 hasConcept C154945302 @default.
- W4294328372 hasConcept C199360897 @default.
- W4294328372 hasConcept C2778770139 @default.
- W4294328372 hasConcept C30038468 @default.
- W4294328372 hasConcept C33923547 @default.
- W4294328372 hasConcept C41008148 @default.
- W4294328372 hasConcept C41895202 @default.
- W4294328372 hasConcept C50644808 @default.
- W4294328372 hasConcept C7149132 @default.
- W4294328372 hasConcept C96147967 @default.
- W4294328372 hasConcept C97541855 @default.
- W4294328372 hasConceptScore W4294328372C111919701 @default.
- W4294328372 hasConceptScore W4294328372C118070581 @default.
- W4294328372 hasConceptScore W4294328372C119857082 @default.
- W4294328372 hasConceptScore W4294328372C138885662 @default.
- W4294328372 hasConceptScore W4294328372C145420912 @default.
- W4294328372 hasConceptScore W4294328372C154945302 @default.
- W4294328372 hasConceptScore W4294328372C199360897 @default.
- W4294328372 hasConceptScore W4294328372C2778770139 @default.
- W4294328372 hasConceptScore W4294328372C30038468 @default.
- W4294328372 hasConceptScore W4294328372C33923547 @default.
- W4294328372 hasConceptScore W4294328372C41008148 @default.
- W4294328372 hasConceptScore W4294328372C41895202 @default.
- W4294328372 hasConceptScore W4294328372C50644808 @default.
- W4294328372 hasConceptScore W4294328372C7149132 @default.
- W4294328372 hasConceptScore W4294328372C96147967 @default.
- W4294328372 hasConceptScore W4294328372C97541855 @default.
- W4294328372 hasLocation W42943283721 @default.
- W4294328372 hasOpenAccess W4294328372 @default.
- W4294328372 hasPrimaryLocation W42943283721 @default.
- W4294328372 hasRelatedWork W2788385947 @default.
- W4294328372 hasRelatedWork W2907922678 @default.
- W4294328372 hasRelatedWork W2954850701 @default.
- W4294328372 hasRelatedWork W2989896317 @default.
- W4294328372 hasRelatedWork W3011591403 @default.
- W4294328372 hasRelatedWork W3022038857 @default.
- W4294328372 hasRelatedWork W3103206163 @default.
- W4294328372 hasRelatedWork W3149805206 @default.
- W4294328372 hasRelatedWork W3181229309 @default.
- W4294328372 hasRelatedWork W1629725936 @default.
- W4294328372 isParatext "false" @default.
- W4294328372 isRetracted "false" @default.
- W4294328372 workType "article" @default.