國立虎尾科技大學 |

登入

回首頁

CortexNet : = A Robust Predictive De...

ProQuest Information and Learning Co.

CortexNet : = A Robust Predictive Deep Neural Network Trained on Videos.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	CortexNet :/
其他題名:	A Robust Predictive Deep Neural Network Trained on Videos.
作者:	Canziani, Alfredo.
面頁冊數:	1 online resource (96 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.
標題:	Artificial intelligence. -
電子資源:	click for full text (PQDT)
ISBN:	9780355254938

CortexNet : = A Robust Predictive Deep Neural Network Trained on Videos.
Canziani, Alfredo.

CortexNet :A Robust Predictive Deep Neural Network Trained on Videos. - 1 online resource (96 pages)

Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.

Thesis (Ph.D.)--Purdue University, 2017.

Includes bibliographical references

In the past five years we have observed the rise of incredibly well performing feed-forward neural networks trained with supervision for vision related tasks. These models have achieved super-human performance on object recognition, localisation, and detection in still images. However, there is a need to identify the best strategy to employ these networks with temporal visual inputs and obtain a robust and stable representation of video data. Inspired by the human visual system, I propose a deep neural network family, CortexNet, which features not only bottom-up feed-forward connections, but also it models the abundant top-down feedback and lateral connections, which are present in our visual cortex. I introduce two training schemes --- the unsupervised MatchNet and weakly supervised TempoNet modes --- where a network learns how to correctly anticipate a subsequent frame in a video clip or the identity of its predominant subject, by learning egomotion cues and how to automatically track several objects in the current scene. Find the project website at tinyurl.com/CortexNet.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355254938Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

CortexNet : = A Robust Predictive Deep Neural Network Trained on Videos.
LDR:02264ntm a2200337K 4500 001 912167
005 20180608102940.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355254938
035 $a (MiAaPQ)AAI10607656
035 $a (MiAaPQ)purdue:21744
035 $a AAI10607656
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Canziani, Alfredo. $3 1184402
245 1 0 $a CortexNet : $b A Robust Predictive Deep Neural Network Trained on Videos.
264 0 $c 2017
300 $a 1 online resource (96 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: Dissertation Abstracts International, Volume: 79-03(E), Section: B.
500 $a Adviser: Eugenio Culurciello.
502 $a Thesis (Ph.D.)--Purdue University, 2017.
504 $a Includes bibliographical references
520 $a In the past five years we have observed the rise of incredibly well performing feed-forward neural networks trained with supervision for vision related tasks. These models have achieved super-human performance on object recognition, localisation, and detection in still images. However, there is a need to identify the best strategy to employ these networks with temporal visual inputs and obtain a robust and stable representation of video data. Inspired by the human visual system, I propose a deep neural network family, CortexNet, which features not only bottom-up feed-forward connections, but also it models the abundant top-down feedback and lateral connections, which are present in our visual cortex. I introduce two training schemes --- the unsupervised MatchNet and weakly supervised TempoNet modes --- where a network learns how to correctly anticipate a subsequent frame in a video clip or the identity of its predominant subject, by learning egomotion cues and how to automatically track several objects in the current scene. Find the project website at tinyurl.com/CortexNet.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Neurosciences. $3 593561
650 4 $a Biomedical engineering. $3 588770
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0317
690 $a 0541
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Purdue University. $b Biomedical Engineering. $3 1184403
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10607656 $z click for full text (PQDT)

筆 0 讀者評論

多媒體

評論

新增評論分享你的心得

Export

取書館別