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

Nature of Learning and Learning of N...

Garg, Shivam.

FindBook

Google Book

Amazon

博客來

Nature of Learning and Learning of Nature.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Nature of Learning and Learning of Nature./
作者:	Garg, Shivam.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
面頁冊數:	242 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-06, Section: B.
Contained By:	Dissertations Abstracts International85-06B.
標題:	Feedback. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30726884
ISBN:	9798381021509

Nature of Learning and Learning of Nature.
Garg, Shivam.

Nature of Learning and Learning of Nature. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 242 p.

Source: Dissertations Abstracts International, Volume: 85-06, Section: B.

Thesis (Ph.D.)--Stanford University, 2023.

This thesis explores questions surrounding the foundations of intelligence, both artificial and natural.The first part focuses on the algorithmic and statistical underpinnings of modern machine learning systems. First, we discuss a clean framework for investigating the surprising ability of large language models to learn in-context: the apparent ability to solve new tasks given just a text prompt that provides examples. Further, motivated by concerns around the insatiable data appetite of modern machine learning systems, we discuss the problem of "sample amplification", where we formalize the seemingly naive question of how hard it is to create new data and contrast the hardness of this task to that of learning the data-generating distribution.The second part considers the algorithmic basis of intelligence in nature, specifically in ant colonies and the brain. We examine how arboreal turtle ants solve variants of the shortest path problem without any central control and with minimal computational resources. In the context of the brain, we study how it manages to train its neural network despite its structural limitations. Specifically, we investigate a biologically plausible learning algorithm and contrast it with gradient descent, arguably the only known algorithm for training large-scale artificial neural networks.

ISBN: 9798381021509Subjects--Topical Terms:

677181
Feedback.

Nature of Learning and Learning of Nature.
LDR:02319nmm a2200313 4500 001 2398318
005 20240812064610.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798381021509
035 $a (MiAaPQ)AAI30726884
035 $a (MiAaPQ)STANFORDtc258nv3060
035 $a AAI30726884
040 $a MiAaPQ $c MiAaPQ
100 1 $a Garg, Shivam. $3 3768231
245 1 0 $a Nature of Learning and Learning of Nature.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 242 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-06, Section: B.
500 $a Advisor: Valiant, Gregory;Charikar, Moses;Tan, Li-Yang.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
520 $a This thesis explores questions surrounding the foundations of intelligence, both artificial and natural.The first part focuses on the algorithmic and statistical underpinnings of modern machine learning systems. First, we discuss a clean framework for investigating the surprising ability of large language models to learn in-context: the apparent ability to solve new tasks given just a text prompt that provides examples. Further, motivated by concerns around the insatiable data appetite of modern machine learning systems, we discuss the problem of "sample amplification", where we formalize the seemingly naive question of how hard it is to create new data and contrast the hardness of this task to that of learning the data-generating distribution.The second part considers the algorithmic basis of intelligence in nature, specifically in ant colonies and the brain. We examine how arboreal turtle ants solve variants of the shortest path problem without any central control and with minimal computational resources. In the context of the brain, we study how it manages to train its neural network despite its structural limitations. Specifically, we investigate a biologically plausible learning algorithm and contrast it with gradient descent, arguably the only known algorithm for training large-scale artificial neural networks.
590 $a School code: 0212.
650 4 $a Feedback. $3 677181
650 4 $a Neural networks. $3 677449
690 $a 0800
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 85-06B.
790 $a 0212
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30726884