FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2977465327> ?p ?o ?g. }

• W2977465327 abstract "Deep learning algorithms have been applied very successfully in recent years to a range of problems out of reach for classical solution paradigms. Nevertheless, there is no completely rigorous mathematical error and convergence analysis which explains the success of deep learning algorithms. The error of a deep learning algorithm can in many situations be decomposed into three parts, the approximation error, the generalization error, and the optimization error. In this work we estimate for a certain deep learning algorithm each of these three errors and combine these three error estimates to obtain an overall error analysis for the deep learning algorithm under consideration. In particular, we thereby establish convergence with a suitable convergence speed for the overall error of the deep learning algorithm under consideration. Our convergence speed analysis is far from optimal and the convergence speed that we establish is rather slow, increases exponentially in the dimensions, and, in particular, suffers from the curse of dimensionality. The main contribution of this work is, instead, to provide a full error analysis (i) which covers each of the three different sources of errors usually emerging in deep learning algorithms and (ii) which merges these three sources of errors into one overall error estimate for the considered deep learning algorithm." @default.
• W2977465327 created "2019-10-10" @default.
• W2977465327 creator A5074382323 @default.
• W2977465327 creator A5084793732 @default.
• W2977465327 creator A5002219954 @default.
• W2977465327 date "2022-04-05" @default.
• W2977465327 modified "2023-10-17" @default.
• W2977465327 title "Full error analysis for the training of deep neural networks" @default.
• W2977465327 cites W1484867920 @default.
• W2977465327 cites W1820164671 @default.
• W2977465327 cites W1971735090 @default.
• W2977465327 cites W1984367183 @default.
• W2977465327 cites W1988115241 @default.
• W2977465327 cites W2002023932 @default.
• W2977465327 cites W2027197837 @default.
• W2977465327 cites W2033137841 @default.
• W2977465327 cites W2047278710 @default.
• W2977465327 cites W2072773743 @default.
• W2977465327 cites W2073492708 @default.
• W2977465327 cites W2079224763 @default.
• W2977465327 cites W2091297126 @default.
• W2977465327 cites W2103496339 @default.
• W2977465327 cites W2113442785 @default.
• W2977465327 cites W2126001294 @default.
• W2977465327 cites W2137983211 @default.
• W2977465327 cites W2157890204 @default.
• W2977465327 cites W2158581396 @default.
• W2977465327 cites W2166116275 @default.
• W2977465327 cites W2267573953 @default.
• W2977465327 cites W2497677836 @default.
• W2977465327 cites W2513671774 @default.
• W2977465327 cites W2528305538 @default.
• W2977465327 cites W2747971139 @default.
• W2977465327 cites W2754833785 @default.
• W2977465327 cites W2786773456 @default.
• W2977465327 cites W2792270552 @default.
• W2977465327 cites W2883486956 @default.
• W2977465327 cites W2885273747 @default.
• W2977465327 cites W2890291741 @default.
• W2977465327 cites W2903857590 @default.
• W2977465327 cites W2914255806 @default.
• W2977465327 cites W2938647293 @default.
• W2977465327 cites W2943191253 @default.
• W2977465327 cites W2962761333 @default.
• W2977465327 cites W2963146412 @default.
• W2977465327 cites W2963172624 @default.
• W2977465327 cites W2965192329 @default.
• W2977465327 cites W2969750612 @default.
• W2977465327 cites W2981407587 @default.
• W2977465327 cites W2982376398 @default.
• W2977465327 cites W2994760360 @default.
• W2977465327 cites W3012168927 @default.
• W2977465327 cites W3023241366 @default.
• W2977465327 cites W3025750359 @default.
• W2977465327 cites W3031715235 @default.
• W2977465327 cites W3100743579 @default.
• W2977465327 cites W3101996726 @default.
• W2977465327 cites W3104183394 @default.
• W2977465327 cites W3125537303 @default.
• W2977465327 cites W3132264265 @default.
• W2977465327 cites W3133816032 @default.
• W2977465327 cites W3157282745 @default.
• W2977465327 cites W3167031531 @default.
• W2977465327 cites W3180808552 @default.
• W2977465327 cites W4229690478 @default.
• W2977465327 cites W4233413206 @default.
• W2977465327 cites W4236362309 @default.
• W2977465327 cites W4236966694 @default.
• W2977465327 cites W4242686374 @default.
• W2977465327 doi "https://doi.org/10.1142/s021902572150020x" @default.
• W2977465327 hasPublicationYear "2022" @default.
• W2977465327 type Work @default.
• W2977465327 sameAs 2977465327 @default.
• W2977465327 citedByCount "16" @default.
• W2977465327 countsByYear W29774653272020 @default.
• W2977465327 countsByYear W29774653272021 @default.
• W2977465327 countsByYear W29774653272022 @default.
• W2977465327 countsByYear W29774653272023 @default.
• W2977465327 crossrefType "journal-article" @default.
• W2977465327 hasAuthorship W2977465327A5002219954 @default.
• W2977465327 hasAuthorship W2977465327A5074382323 @default.
• W2977465327 hasAuthorship W2977465327A5084793732 @default.
• W2977465327 hasBestOaLocation W29774653272 @default.
• W2977465327 hasConcept C108583219 @default.
• W2977465327 hasConcept C111030470 @default.
• W2977465327 hasConcept C11413529 @default.
• W2977465327 hasConcept C117765406 @default.
• W2977465327 hasConcept C119857082 @default.
• W2977465327 hasConcept C122383733 @default.
• W2977465327 hasConcept C134306372 @default.
• W2977465327 hasConcept C154945302 @default.
• W2977465327 hasConcept C159985019 @default.
• W2977465327 hasConcept C162324750 @default.
• W2977465327 hasConcept C177148314 @default.
• W2977465327 hasConcept C192562407 @default.
• W2977465327 hasConcept C204323151 @default.
• W2977465327 hasConcept C2777303404 @default.
• W2977465327 hasConcept C28826006 @default.
• W2977465327 hasConcept C3018824978 @default.
• W2977465327 hasConcept C33923547 @default.

• next