FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133671113> ?p ?o ?g. }

• W3133671113 abstract "In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector. Their unordered nature makes them suitable for modeling a wide variety of data, ranging from objects in images to point clouds to graphs. Deep learning has recently shown great success on other types of structured data, so we aim to build the necessary structures for sets into deep neural networks. The first focus of this thesis is the learning of better set representations (sets as input). Existing approaches have bottlenecks that prevent them from properly modeling relations between objects within the set. To address this issue, we develop a variety of techniques for different scenarios and show that alleviating the bottleneck leads to consistent improvements across many experiments. The second focus of this thesis is the prediction of sets (sets as output). Current approaches do not take the unordered nature of sets into account properly. We determine that this results in a problem that causes discontinuity issues with many set prediction tasks and prevents them from learning some extremely simple datasets. To avoid this problem, we develop two models that properly take the structure of sets into account. Various experiments show that our set prediction techniques can significantly benefit over existing approaches." @default.
• W3133671113 created "2021-03-15" @default.
• W3133671113 creator A5086664284 @default.
• W3133671113 date "2021-03-08" @default.
• W3133671113 modified "2023-09-27" @default.
• W3133671113 title "Learning to Represent and Predict Sets with Deep Neural Networks." @default.
• W3133671113 cites W1665115054 @default.
• W3133671113 cites W1836465849 @default.
• W3133671113 cites W1903029394 @default.
• W3133671113 cites W1933349210 @default.
• W3133671113 cites W1966443646 @default.
• W3133671113 cites W1990283121 @default.
• W3133671113 cites W2031494345 @default.
• W3133671113 cites W2064675550 @default.
• W3133671113 cites W2089808326 @default.
• W3133671113 cites W2095705004 @default.
• W3133671113 cites W2103496339 @default.
• W3133671113 cites W2112796928 @default.
• W3133671113 cites W2141399712 @default.
• W3133671113 cites W2142498761 @default.
• W3133671113 cites W2143331230 @default.
• W3133671113 cites W2145983039 @default.
• W3133671113 cites W2147527908 @default.
• W3133671113 cites W2149029960 @default.
• W3133671113 cites W2186629860 @default.
• W3133671113 cites W2187061624 @default.
• W3133671113 cites W2194775991 @default.
• W3133671113 cites W2296073425 @default.
• W3133671113 cites W2321533354 @default.
• W3133671113 cites W2471094925 @default.
• W3133671113 cites W2484273982 @default.
• W3133671113 cites W2514087538 @default.
• W3133671113 cites W2560609797 @default.
• W3133671113 cites W2560722161 @default.
• W3133671113 cites W2560730294 @default.
• W3133671113 cites W2561715562 @default.
• W3133671113 cites W2606014079 @default.
• W3133671113 cites W2606884824 @default.
• W3133671113 cites W2608030593 @default.
• W3133671113 cites W2612624696 @default.
• W3133671113 cites W2624614404 @default.
• W3133671113 cites W2626778328 @default.
• W3133671113 cites W2745461083 @default.
• W3133671113 cites W2747623286 @default.
• W3133671113 cites W2750894112 @default.
• W3133671113 cites W2768308213 @default.
• W3133671113 cites W2770567114 @default.
• W3133671113 cites W2780786077 @default.
• W3133671113 cites W2784996692 @default.
• W3133671113 cites W2786103815 @default.
• W3133671113 cites W2788919350 @default.
• W3133671113 cites W2796426482 @default.
• W3133671113 cites W2798979442 @default.
• W3133671113 cites W2804243936 @default.
• W3133671113 cites W2806115886 @default.
• W3133671113 cites W2806351858 @default.
• W3133671113 cites W2899038170 @default.
• W3133671113 cites W2907502844 @default.
• W3133671113 cites W2910992787 @default.
• W3133671113 cites W2912177220 @default.
• W3133671113 cites W2919112510 @default.
• W3133671113 cites W2949847915 @default.
• W3133671113 cites W2952832237 @default.
• W3133671113 cites W2953106684 @default.
• W3133671113 cites W2962676885 @default.
• W3133671113 cites W2962711740 @default.
• W3133671113 cites W2962851953 @default.
• W3133671113 cites W2962933067 @default.
• W3133671113 cites W2963037478 @default.
• W3133671113 cites W2963223524 @default.
• W3133671113 cites W2963376432 @default.
• W3133671113 cites W2963506485 @default.
• W3133671113 cites W2963513093 @default.
• W3133671113 cites W2963549470 @default.
• W3133671113 cites W2963668159 @default.
• W3133671113 cites W2963686699 @default.
• W3133671113 cites W2963693726 @default.
• W3133671113 cites W2963703618 @default.
• W3133671113 cites W2963716836 @default.
• W3133671113 cites W2963907708 @default.
• W3133671113 cites W2963921132 @default.
• W3133671113 cites W2963954913 @default.
• W3133671113 cites W2964036520 @default.
• W3133671113 cites W2964080601 @default.
• W3133671113 cites W2964108670 @default.
• W3133671113 cites W2964121744 @default.
• W3133671113 cites W2964205912 @default.
• W3133671113 cites W2964294232 @default.
• W3133671113 cites W2964308564 @default.
• W3133671113 cites W2964316651 @default.
• W3133671113 cites W2964345214 @default.
• W3133671113 cites W2970638480 @default.
• W3133671113 cites W2971081194 @default.
• W3133671113 cites W2978204343 @default.
• W3133671113 cites W3118608800 @default.
• W3133671113 cites W607748843 @default.
• W3133671113 hasPublicationYear "2021" @default.
• W3133671113 type Work @default.
• W3133671113 sameAs 3133671113 @default.
• W3133671113 citedByCount "0" @default.

• next