東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Mechanisms of Computation and Learni...

Sorscher, Benjamin David,

Linked to FindBook

Google Book

Amazon

博客來

Mechanisms of Computation and Learning in Neural Networks /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Mechanisms of Computation and Learning in Neural Networks // Benjamin David Sorscher.
Author:	Sorscher, Benjamin David,
Description:	1 electronic resource (135 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-10, Section: B.
Contained By:	Dissertations Abstracts International86-10B.
Subject:	Sparsity. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31974666
ISBN:	9798311963947

Mechanisms of Computation and Learning in Neural Networks /
Sorscher, Benjamin David,

Mechanisms of Computation and Learning in Neural Networks /Benjamin David Sorscher. - 1 electronic resource (135 pages)

Source: Dissertations Abstracts International, Volume: 86-10, Section: B.

Our ability to perceive the world, to navigate through it, to acquire new knowledge and learn new concepts, to hunt prey or evade predators, to do science or art or form relationships, is mediated by networks of neurons in the brain. These same neurons (or at least superficially very similar ones) can be found in worms, flies, mice, monkeys, and in the artificial neural networks of modern AI systems. How do these individually simple units, when wired together in complex ways, give rise to such intricate and diverse behaviors? Are the computational principles underlying these neural circuits conserved between flies and mice and humans? What about artificial neural networks? How much of the structure in neural networks in the brain is innate - "hard-wired" by evolution - and how much is acquired during the lifetime of an organism learning and interacting with its environment?The work presented in this thesis relies on many insights and frameworks for understanding computation in the brain from neuroscientists, physicists, and computer scientists, over many decades. We will introduce these ideas in this chapter, beginning by framing the challenges of understanding computation in neural circuits and discussing at what level such an understanding might be possible. In the following chapters, we will draw on diverse examples from the navigation system in rodents, to concept learning in primates, to AI systems for vision and language, to study how computations are performed in these neural circuits, and to investigate how learning is alike and di!erent across species and between humans and artificial neural networks.

English

ISBN: 9798311963947Subjects--Topical Terms:

3680690
Sparsity.

Mechanisms of Computation and Learning in Neural Networks /
LDR:02923nmm a22003733i 4500 001 2432684
005 20250731101912.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798311963947
035 $a (MiAaPQD)AAI31974666
035 $a (MiAaPQD)Stanfordvm453fc6825
035 $a AAI31974666
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Sorscher, Benjamin David, $e author. $3 3822002
245 1 0 $a Mechanisms of Computation and Learning in Neural Networks / $c Benjamin David Sorscher.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (135 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-10, Section: B.
500 $a Advisors: Ganguli, Surya Committee members: Giocomo, Lisa; Good, Benjamin; Bent, Stacey F.
502 $b Ph.D. $c Stanford University $d 2025.
520 $a Our ability to perceive the world, to navigate through it, to acquire new knowledge and learn new concepts, to hunt prey or evade predators, to do science or art or form relationships, is mediated by networks of neurons in the brain. These same neurons (or at least superficially very similar ones) can be found in worms, flies, mice, monkeys, and in the artificial neural networks of modern AI systems. How do these individually simple units, when wired together in complex ways, give rise to such intricate and diverse behaviors? Are the computational principles underlying these neural circuits conserved between flies and mice and humans? What about artificial neural networks? How much of the structure in neural networks in the brain is innate - "hard-wired" by evolution - and how much is acquired during the lifetime of an organism learning and interacting with its environment?The work presented in this thesis relies on many insights and frameworks for understanding computation in the brain from neuroscientists, physicists, and computer scientists, over many decades. We will introduce these ideas in this chapter, beginning by framing the challenges of understanding computation in neural circuits and discussing at what level such an understanding might be possible. In the following chapters, we will draw on diverse examples from the navigation system in rodents, to concept learning in primates, to AI systems for vision and language, to study how computations are performed in these neural circuits, and to investigate how learning is alike and di!erent across species and between humans and artificial neural networks.
546 $a English
590 $a School code: 0212
650 4 $a Sparsity. $3 3680690
650 4 $a Cells. $3 634126
650 4 $a Neurons. $3 588699
650 4 $a Physics. $3 516296
650 4 $a Fourier transforms. $3 3545926
650 4 $a Memory. $3 522110
650 4 $a Neural networks. $3 677449
650 4 $a Brain. $3 525115
650 4 $a Cognitive models. $3 3686958
650 4 $a Insects. $3 516323
650 4 $a Neurosciences. $3 588700
650 4 $a Animal cognition. $3 3563972
650 4 $a Geometry. $3 517251
650 4 $a Virtual reality. $3 527460
690 $a 0317
690 $a 0605
710 2 $a Stanford University. $e degree granting institution. $3 3765820
720 1 $a Ganguli, Surya $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-10B.
790 $a 0212
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31974666