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

Deep learning to see = towards new f...

Betti, Alessandro.

Linked to FindBook

Google Book

Amazon

博客來

Deep learning to see = towards new foundations of computer vision /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deep learning to see/ by Alessandro Betti, Marco Gori, Stefano Melacci.
Reminder of title:	towards new foundations of computer vision /
Author:	Betti, Alessandro.
other author:	Gori, Marco.
Published:	Cham :Springer International Publishing : : 2022.,
Description:	xiv, 105 p. :ill. (some col.), digital ;24 cm.
[NT 15003449]:	1. Introduction -- 2. Cutting the Umbilical Cord with Pattern Recognition -- 3. Spatiotemporal Visual Environments -- 4. Hierarchical Description of Visual Tasks -- 5. Benchmarks and the "En Plein Air" Challenge.
Contained By:	Springer Nature eBook
Subject:	Computer vision. -
Online resource:	https://doi.org/10.1007/978-3-030-90987-1
ISBN:	9783030909871

Deep learning to see = towards new foundations of computer vision /
Betti, Alessandro.

Deep learning to seetowards new foundations of computer vision /[electronic resource] :by Alessandro Betti, Marco Gori, Stefano Melacci. - Cham :Springer International Publishing :2022. - xiv, 105 p. :ill. (some col.), digital ;24 cm. - SpringerBriefs in computer science,2191-5776. - SpringerBriefs in computer science..

1. Introduction -- 2. Cutting the Umbilical Cord with Pattern Recognition -- 3. Spatiotemporal Visual Environments -- 4. Hierarchical Description of Visual Tasks -- 5. Benchmarks and the "En Plein Air" Challenge.

The remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm. While subscribing to this view, this book criticizes the supposed scientific progress in the field, and proposes the investigation of vision within the framework of information-based laws of nature. Specifically, the present work poses fundamental questions about vision that remain far from understood, leading the reader on a journey populated by novel challenges resonating with the foundations of machine learning. The central thesis is that for a deeper understanding of visual computational processes, it is necessary to look beyond the applications of general purpose machine learning algorithms, and focus instead on appropriate learning theories that take into account the spatiotemporal nature of the visual signal. Topics and features: Presents a curiosity-driven approach, posing questions to stimulate readers to design novel computational models of vision Offers a rethinking of computer vision, arguing for an approach based on vision in nature, versus regarding visual signals as collections of images Provides an interdisciplinary commentary, aiming to unify computer vision, machine learning, human vision, and computational neuroscience Serving to inspire and stimulate critical reflection and discussion, yet requiring no prior advanced technical knowledge, the text can naturally be paired with classic textbooks on computer vision to better frame the current state of the art, open problems, and novel potential solutions. This unique volume will be of great benefit to graduate and advanced undergraduate students in computer science, computational neuroscience, physics, and other related disciplines.

ISBN: 9783030909871

Standard No.: 10.1007/978-3-030-90987-1doiSubjects--Topical Terms:

540671
Computer vision.

LC Class. No.: TA1634 / .B47 2022

Dewey Class. No.: 006.37

Deep learning to see = towards new foundations of computer vision /
LDR:03157nmm a2200337 a 4500 001 2299891
003 DE-He213
005 20220426134951.0
006 m d
007 cr nn 008maaau
008 230324s2022 sz s 0 eng d
020 $a 9783030909871 $q (electronic bk.)
020 $a 9783030909864 $q (paper)
024 7 $a 10.1007/978-3-030-90987-1 $2 doi
035 $a 978-3-030-90987-1
040 $a GP $c GP
041 0 $a eng
050 4 $a TA1634 $b .B47 2022
072 7 $a UYQV $2 bicssc
072 7 $a COM012000 $2 bisacsh
072 7 $a UYQV $2 thema
082 0 4 $a 006.37 $2 23
090 $a TA1634 $b .B565 2022
100 1 $a Betti, Alessandro. $3 3597787
245 1 0 $a Deep learning to see $h [electronic resource] : $b towards new foundations of computer vision / $c by Alessandro Betti, Marco Gori, Stefano Melacci.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a xiv, 105 p. : $b ill. (some col.), digital ; $c 24 cm.
490 1 $a SpringerBriefs in computer science, $x 2191-5776
505 0 $a 1. Introduction -- 2. Cutting the Umbilical Cord with Pattern Recognition -- 3. Spatiotemporal Visual Environments -- 4. Hierarchical Description of Visual Tasks -- 5. Benchmarks and the "En Plein Air" Challenge.
520 $a The remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm. While subscribing to this view, this book criticizes the supposed scientific progress in the field, and proposes the investigation of vision within the framework of information-based laws of nature. Specifically, the present work poses fundamental questions about vision that remain far from understood, leading the reader on a journey populated by novel challenges resonating with the foundations of machine learning. The central thesis is that for a deeper understanding of visual computational processes, it is necessary to look beyond the applications of general purpose machine learning algorithms, and focus instead on appropriate learning theories that take into account the spatiotemporal nature of the visual signal. Topics and features: Presents a curiosity-driven approach, posing questions to stimulate readers to design novel computational models of vision Offers a rethinking of computer vision, arguing for an approach based on vision in nature, versus regarding visual signals as collections of images Provides an interdisciplinary commentary, aiming to unify computer vision, machine learning, human vision, and computational neuroscience Serving to inspire and stimulate critical reflection and discussion, yet requiring no prior advanced technical knowledge, the text can naturally be paired with classic textbooks on computer vision to better frame the current state of the art, open problems, and novel potential solutions. This unique volume will be of great benefit to graduate and advanced undergraduate students in computer science, computational neuroscience, physics, and other related disciplines.
650 0 $a Computer vision. $3 540671
650 0 $a Deep learning (Machine learning) $3 3538509
650 1 4 $a Computer Vision. $3 3538524
650 2 4 $a Machine Learning. $3 3382522
650 2 4 $a Computational Neuroscience. $3 3593148
650 2 4 $a Vision and Colour Science. $3 3597789
700 1 $a Gori, Marco. $3 1069969
700 1 $a Melacci, Stefano. $3 3597788
710 2 $a SpringerLink (Online service) $3 836513
773 0 $t Springer Nature eBook
830 0 $a SpringerBriefs in computer science. $3 1567571
856 4 0 $u https://doi.org/10.1007/978-3-030-90987-1
950 $a Computer Science (SpringerNature-11645)