Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386728362> ?p ?o ?g. }
Showing items 1 to 48 of
48
with 100 items per page.
- W4386728362 endingPage "27" @default.
- W4386728362 startingPage "13" @default.
- W4386728362 abstract "Since the groundbreaking performance improvement by AlexNet at the ImageNet challenge, deep learning has provided significant gains over classical approaches in various fields of data science including imaging reconstruction. The availability of large-scale training datasets and advances in neural network research have resulted in the unprecedented success of deep learning in various applications. Nonetheless, the success of deep learning appears very mysterious. The basic building blocks of deep neural networks are convolution, pooling, and nonlinearity, which are primitive tools of mathematics. Interestingly, the cascaded connection of these primitive tools results in superior performance over traditional approaches. To understand this mystery, one can go back to the basic ideas of the classical approaches to understand the similarities and differences from modern deep-neural-network methods. In this chapter, we explain the limitations of the classical machine learning approaches, and provide a review of mathematical foundations to understand why deep neural networks have successfully overcome their limitations." @default.
- W4386728362 created "2023-09-15" @default.
- W4386728362 creator A5012644755 @default.
- W4386728362 creator A5046939141 @default.
- W4386728362 date "2023-09-30" @default.
- W4386728362 modified "2023-09-27" @default.
- W4386728362 title "Geometry of Deep Learning" @default.
- W4386728362 doi "https://doi.org/10.1017/9781009042529.004" @default.
- W4386728362 hasPublicationYear "2023" @default.
- W4386728362 type Work @default.
- W4386728362 citedByCount "0" @default.
- W4386728362 crossrefType "book-chapter" @default.
- W4386728362 hasAuthorship W4386728362A5012644755 @default.
- W4386728362 hasAuthorship W4386728362A5046939141 @default.
- W4386728362 hasConcept C108583219 @default.
- W4386728362 hasConcept C119857082 @default.
- W4386728362 hasConcept C154945302 @default.
- W4386728362 hasConcept C2984842247 @default.
- W4386728362 hasConcept C41008148 @default.
- W4386728362 hasConcept C50644808 @default.
- W4386728362 hasConcept C70437156 @default.
- W4386728362 hasConcept C81363708 @default.
- W4386728362 hasConceptScore W4386728362C108583219 @default.
- W4386728362 hasConceptScore W4386728362C119857082 @default.
- W4386728362 hasConceptScore W4386728362C154945302 @default.
- W4386728362 hasConceptScore W4386728362C2984842247 @default.
- W4386728362 hasConceptScore W4386728362C41008148 @default.
- W4386728362 hasConceptScore W4386728362C50644808 @default.
- W4386728362 hasConceptScore W4386728362C70437156 @default.
- W4386728362 hasConceptScore W4386728362C81363708 @default.
- W4386728362 hasLocation W43867283621 @default.
- W4386728362 hasOpenAccess W4386728362 @default.
- W4386728362 hasPrimaryLocation W43867283621 @default.
- W4386728362 hasRelatedWork W2279398222 @default.
- W4386728362 hasRelatedWork W2517027266 @default.
- W4386728362 hasRelatedWork W2915754718 @default.
- W4386728362 hasRelatedWork W2955560448 @default.
- W4386728362 hasRelatedWork W3000866861 @default.
- W4386728362 hasRelatedWork W4299822940 @default.
- W4386728362 hasRelatedWork W4312417841 @default.
- W4386728362 hasRelatedWork W4321369474 @default.
- W4386728362 hasRelatedWork W4385681650 @default.
- W4386728362 hasRelatedWork W2551883569 @default.
- W4386728362 isParatext "false" @default.
- W4386728362 isRetracted "false" @default.
- W4386728362 workType "book-chapter" @default.