東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Geometric Aspects of Deep Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Geometric Aspects of Deep Learning./
作者:	Fort, Stanislav.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	106 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-09, Section: B.
Contained By:	Dissertations Abstracts International83-09B.
標題:	Deep learning. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29003878
ISBN:	9798209789888

Geometric Aspects of Deep Learning.
Fort, Stanislav.

Geometric Aspects of Deep Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 106 p.

Source: Dissertations Abstracts International, Volume: 83-09, Section: B.

Thesis (Ph.D.)--Stanford University, 2021.

This item must not be sold to any third party vendors.

Machine learning using deep neural networks -- deep learning -- has been extremely successful at learning solutions to a very broad suite of difficult problems across a wide range of domains spanning computer vision, game play, natural language processing and understanding, and even fundamental science. Despite this success, we still do not have a detailed, predictive understanding of how deep neural networks work, and what makes them so effective at learning and generalization. In this thesis we study the loss landscapes of deep neural networks using the lens of high-dimensional geometry.We approach the problem of understanding deep neural networks experimentally, similarly to the methods used in the natural sciences. We first discuss a phenomenological approach to modeling the large scale structure of deep neural network loss landscapes using high-dimensional geometry. Using this model, we then continue to investigate the diversity of functions neural networks learn and how it relates to the underlying geometric structure of the solution manifold. We focus on deep ensembles, robustness, and on approximate Bayesian techniques.Finally, we switch gears and investigate the role of nonlinearity in deep learning. We study deep neural networks within the Neural Tangent Kernel framework and empirically establish the role of nonlinearity for the training dynamics of finite-size networks. Using the concept of the nonlinear advantage, we empirically demonstrate the importance of nonlinearity in the very early phases of training, and its waning role farther into optimization.

ISBN: 9798209789888Subjects--Topical Terms:

3554982
Deep learning.

Geometric Aspects of Deep Learning.
LDR:02605nmm a2200313 4500 001 2345737
005 20220613063807.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798209789888
035 $a (MiAaPQ)AAI29003878
035 $a (MiAaPQ)STANFORDjk243mm2141
035 $a AAI29003878
040 $a MiAaPQ $c MiAaPQ
100 1 $a Fort, Stanislav. $3 3684732
245 1 0 $a Geometric Aspects of Deep Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 106 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-09, Section: B.
500 $a Advisor: Ganguli, Surya;Shenker, Stephen Hart;Yamins, Daniel.
502 $a Thesis (Ph.D.)--Stanford University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Machine learning using deep neural networks -- deep learning -- has been extremely successful at learning solutions to a very broad suite of difficult problems across a wide range of domains spanning computer vision, game play, natural language processing and understanding, and even fundamental science. Despite this success, we still do not have a detailed, predictive understanding of how deep neural networks work, and what makes them so effective at learning and generalization. In this thesis we study the loss landscapes of deep neural networks using the lens of high-dimensional geometry.We approach the problem of understanding deep neural networks experimentally, similarly to the methods used in the natural sciences. We first discuss a phenomenological approach to modeling the large scale structure of deep neural network loss landscapes using high-dimensional geometry. Using this model, we then continue to investigate the diversity of functions neural networks learn and how it relates to the underlying geometric structure of the solution manifold. We focus on deep ensembles, robustness, and on approximate Bayesian techniques.Finally, we switch gears and investigate the role of nonlinearity in deep learning. We study deep neural networks within the Neural Tangent Kernel framework and empirically establish the role of nonlinearity for the training dynamics of finite-size networks. Using the concept of the nonlinear advantage, we empirically demonstrate the importance of nonlinearity in the very early phases of training, and its waning role farther into optimization.
590 $a School code: 0212.
650 4 $a Deep learning. $3 3554982
650 4 $a Optimization. $3 891104
650 4 $a Neural networks. $3 677449
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
690 $a 0800
690 $a 0984
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 83-09B.
790 $a 0212
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29003878