FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208499827> ?p ?o ?g. }

• W3208499827 abstract "Series expansions have been a cornerstone of applied mathematics and engineering for centuries. In this paper, we revisit the Taylor series expansion from a modern Machine Learning perspective. Specifically, we introduce the Fast Continuous Convolutional Taylor Transform (FC2T2), a variant of the Fast Multipole Method (FMM), that allows for the efficient approximation of low dimensional convolutional operators in continuous space. We build upon the FMM which is an approximate algorithm that reduces the computational complexity of N-body problems from O(NM) to O(N+M) and finds application in e.g. particle simulations. As an intermediary step, the FMM produces a series expansion for every cell on a grid and we introduce algorithms that act directly upon this representation. These algorithms analytically but approximately compute the quantities required for the forward and backward pass of the backpropagation algorithm and can therefore be employed as (implicit) layers in Neural Networks. Specifically, we introduce a root-implicit layer that outputs surface normals and object distances as well as an integral-implicit layer that outputs a rendering of a radiance field given a 3D pose. In the context of Machine Learning, $N$ and $M$ can be understood as the number of model parameters and model evaluations respectively which entails that, for applications that require repeated function evaluations which are prevalent in Computer Vision and Graphics, unlike regular Neural Networks, the techniques introduce in this paper scale gracefully with parameters. For some applications, this results in a 200x reduction in FLOPs compared to state-of-the-art approaches at a reasonable or non-existent loss in accuracy." @default.
• W3208499827 created "2021-11-08" @default.
• W3208499827 creator A5078707945 @default.
• W3208499827 creator A5083450863 @default.
• W3208499827 date "2021-10-29" @default.
• W3208499827 modified "2023-09-27" @default.
• W3208499827 title "FC2T2: The Fast Continuous Convolutional Taylor Transform with Applications in Vision and Graphics." @default.
• W3208499827 cites W1498436455 @default.
• W3208499827 cites W1538131130 @default.
• W3208499827 cites W183071939 @default.
• W3208499827 cites W1977758817 @default.
• W3208499827 cites W1978978100 @default.
• W3208499827 cites W2046353934 @default.
• W3208499827 cites W2051395078 @default.
• W3208499827 cites W2059447468 @default.
• W3208499827 cites W2073700113 @default.
• W3208499827 cites W2083206954 @default.
• W3208499827 cites W2092686707 @default.
• W3208499827 cites W2103755321 @default.
• W3208499827 cites W2104266187 @default.
• W3208499827 cites W2109760930 @default.
• W3208499827 cites W2133385272 @default.
• W3208499827 cites W2146558186 @default.
• W3208499827 cites W2154011553 @default.
• W3208499827 cites W2161446118 @default.
• W3208499827 cites W2165916500 @default.
• W3208499827 cites W2165977514 @default.
• W3208499827 cites W2171784600 @default.
• W3208499827 cites W2172039283 @default.
• W3208499827 cites W2201021190 @default.
• W3208499827 cites W2417863416 @default.
• W3208499827 cites W2558748708 @default.
• W3208499827 cites W2805499196 @default.
• W3208499827 cites W2808746463 @default.
• W3208499827 cites W2891186417 @default.
• W3208499827 cites W2897097528 @default.
• W3208499827 cites W2919115771 @default.
• W3208499827 cites W2950967261 @default.
• W3208499827 cites W2954698171 @default.
• W3208499827 cites W2962849139 @default.
• W3208499827 cites W2963108750 @default.
• W3208499827 cites W2963527086 @default.
• W3208499827 cites W2963627347 @default.
• W3208499827 cites W2963739349 @default.
• W3208499827 cites W2963926543 @default.
• W3208499827 cites W2963970238 @default.
• W3208499827 cites W2964121028 @default.
• W3208499827 cites W2981603589 @default.
• W3208499827 cites W2981965970 @default.
• W3208499827 cites W2990173985 @default.
• W3208499827 cites W3008102851 @default.
• W3208499827 cites W3008606616 @default.
• W3208499827 cites W3034266912 @default.
• W3208499827 cites W3035524985 @default.
• W3208499827 cites W3036157773 @default.
• W3208499827 cites W3037265641 @default.
• W3208499827 cites W3037676149 @default.
• W3208499827 cites W3048916779 @default.
• W3208499827 cites W3092923133 @default.
• W3208499827 cites W3096986660 @default.
• W3208499827 cites W3099878876 @default.
• W3208499827 cites W3100398946 @default.
• W3208499827 cites W3109585842 @default.
• W3208499827 cites W3129071058 @default.
• W3208499827 cites W94523489 @default.
• W3208499827 hasPublicationYear "2021" @default.
• W3208499827 type Work @default.
• W3208499827 sameAs 3208499827 @default.
• W3208499827 citedByCount "0" @default.
• W3208499827 crossrefType "posted-content" @default.
• W3208499827 hasAuthorship W3208499827A5078707945 @default.
• W3208499827 hasAuthorship W3208499827A5083450863 @default.
• W3208499827 hasConcept C108583219 @default.
• W3208499827 hasConcept C11413529 @default.
• W3208499827 hasConcept C134306372 @default.
• W3208499827 hasConcept C154945302 @default.
• W3208499827 hasConcept C158946198 @default.
• W3208499827 hasConcept C205711294 @default.
• W3208499827 hasConcept C33923547 @default.
• W3208499827 hasConcept C41008148 @default.
• W3208499827 hasConcept C81363708 @default.
• W3208499827 hasConceptScore W3208499827C108583219 @default.
• W3208499827 hasConceptScore W3208499827C11413529 @default.
• W3208499827 hasConceptScore W3208499827C134306372 @default.
• W3208499827 hasConceptScore W3208499827C154945302 @default.
• W3208499827 hasConceptScore W3208499827C158946198 @default.
• W3208499827 hasConceptScore W3208499827C205711294 @default.
• W3208499827 hasConceptScore W3208499827C33923547 @default.
• W3208499827 hasConceptScore W3208499827C41008148 @default.
• W3208499827 hasConceptScore W3208499827C81363708 @default.
• W3208499827 hasLocation W32084998271 @default.
• W3208499827 hasOpenAccess W3208499827 @default.
• W3208499827 hasPrimaryLocation W32084998271 @default.
• W3208499827 hasRelatedWork W2004085757 @default.
• W3208499827 hasRelatedWork W2117735346 @default.
• W3208499827 hasRelatedWork W2203422926 @default.
• W3208499827 hasRelatedWork W2217632068 @default.
• W3208499827 hasRelatedWork W2473578035 @default.
• W3208499827 hasRelatedWork W2612359487 @default.
• W3208499827 hasRelatedWork W2624229329 @default.

• next