Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385714017> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4385714017 abstract "A modern challenge of Artificial Intelligence is learning multiple patterns at once (i.e.parallel learning). While this can not be accomplished by standard Hebbian associative neural networks, in this paper we show how the Multitasking Hebbian Network (a variation on theme of the Hopfield model working on sparse data-sets) is naturally able to perform this complex task. We focus on systems processing in parallel a finite (up to logarithmic growth in the size of the network) amount of patterns, mirroring the low-storage level of standard associative neural networks at work with pattern recognition. For mild dilution in the patterns, the network handles them hierarchically, distributing the amplitudes of their signals as power-laws w.r.t. their information content (hierarchical regime), while, for strong dilution, all the signals pertaining to all the patterns are raised with the same strength (parallel regime). Further, confined to the low-storage setting (i.e., far from the spin glass limit), the presence of a teacher neither alters the multitasking performances nor changes the thresholds for learning: the latter are the same whatever the training protocol is supervised or unsupervised. Results obtained through statistical mechanics, signal-to-noise technique and Monte Carlo simulations are overall in perfect agreement and carry interesting insights on multiple learning at once: for instance, whenever the cost-function of the model is minimized in parallel on several patterns (in its description via Statistical Mechanics), the same happens to the standard sum-squared error Loss function (typically used in Machine Learning)." @default.
- W4385714017 created "2023-08-10" @default.
- W4385714017 creator A5011672584 @default.
- W4385714017 creator A5041457930 @default.
- W4385714017 creator A5056141397 @default.
- W4385714017 creator A5077516005 @default.
- W4385714017 date "2023-08-08" @default.
- W4385714017 modified "2023-09-23" @default.
- W4385714017 title "Parallel Learning by Multitasking Neural Networks" @default.
- W4385714017 doi "https://doi.org/10.48550/arxiv.2308.04106" @default.
- W4385714017 hasPublicationYear "2023" @default.
- W4385714017 type Work @default.
- W4385714017 citedByCount "0" @default.
- W4385714017 crossrefType "posted-content" @default.
- W4385714017 hasAuthorship W4385714017A5011672584 @default.
- W4385714017 hasAuthorship W4385714017A5041457930 @default.
- W4385714017 hasAuthorship W4385714017A5056141397 @default.
- W4385714017 hasAuthorship W4385714017A5077516005 @default.
- W4385714017 hasBestOaLocation W43857140171 @default.
- W4385714017 hasConcept C107418235 @default.
- W4385714017 hasConcept C111437709 @default.
- W4385714017 hasConcept C117765406 @default.
- W4385714017 hasConcept C120822770 @default.
- W4385714017 hasConcept C121332964 @default.
- W4385714017 hasConcept C121864883 @default.
- W4385714017 hasConcept C154945302 @default.
- W4385714017 hasConcept C15744967 @default.
- W4385714017 hasConcept C169760540 @default.
- W4385714017 hasConcept C17061570 @default.
- W4385714017 hasConcept C180747234 @default.
- W4385714017 hasConcept C2779127903 @default.
- W4385714017 hasConcept C2983526489 @default.
- W4385714017 hasConcept C41008148 @default.
- W4385714017 hasConcept C46421273 @default.
- W4385714017 hasConcept C50644808 @default.
- W4385714017 hasConcept C8038995 @default.
- W4385714017 hasConcept C8521452 @default.
- W4385714017 hasConcept C86803240 @default.
- W4385714017 hasConcept C97108695 @default.
- W4385714017 hasConcept C99874945 @default.
- W4385714017 hasConceptScore W4385714017C107418235 @default.
- W4385714017 hasConceptScore W4385714017C111437709 @default.
- W4385714017 hasConceptScore W4385714017C117765406 @default.
- W4385714017 hasConceptScore W4385714017C120822770 @default.
- W4385714017 hasConceptScore W4385714017C121332964 @default.
- W4385714017 hasConceptScore W4385714017C121864883 @default.
- W4385714017 hasConceptScore W4385714017C154945302 @default.
- W4385714017 hasConceptScore W4385714017C15744967 @default.
- W4385714017 hasConceptScore W4385714017C169760540 @default.
- W4385714017 hasConceptScore W4385714017C17061570 @default.
- W4385714017 hasConceptScore W4385714017C180747234 @default.
- W4385714017 hasConceptScore W4385714017C2779127903 @default.
- W4385714017 hasConceptScore W4385714017C2983526489 @default.
- W4385714017 hasConceptScore W4385714017C41008148 @default.
- W4385714017 hasConceptScore W4385714017C46421273 @default.
- W4385714017 hasConceptScore W4385714017C50644808 @default.
- W4385714017 hasConceptScore W4385714017C8038995 @default.
- W4385714017 hasConceptScore W4385714017C8521452 @default.
- W4385714017 hasConceptScore W4385714017C86803240 @default.
- W4385714017 hasConceptScore W4385714017C97108695 @default.
- W4385714017 hasConceptScore W4385714017C99874945 @default.
- W4385714017 hasLocation W43857140171 @default.
- W4385714017 hasOpenAccess W4385714017 @default.
- W4385714017 hasPrimaryLocation W43857140171 @default.
- W4385714017 hasRelatedWork W1483579134 @default.
- W4385714017 hasRelatedWork W1520894008 @default.
- W4385714017 hasRelatedWork W1530541224 @default.
- W4385714017 hasRelatedWork W2026544443 @default.
- W4385714017 hasRelatedWork W2059932101 @default.
- W4385714017 hasRelatedWork W2141247461 @default.
- W4385714017 hasRelatedWork W2159992686 @default.
- W4385714017 hasRelatedWork W2899454144 @default.
- W4385714017 hasRelatedWork W4213041478 @default.
- W4385714017 hasRelatedWork W4321853849 @default.
- W4385714017 isParatext "false" @default.
- W4385714017 isRetracted "false" @default.
- W4385714017 workType "article" @default.