國立虎尾科技大學 |

Neural Encoding and Decoding with Deep Learning for Natural Vision.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Neural Encoding and Decoding with Deep Learning for Natural Vision./
作者:	Wen, Haiguang.
面頁冊數:	1 online resource (161 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
Contained By:	Dissertation Abstracts International79-10B(E).
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9780438018075

Neural Encoding and Decoding with Deep Learning for Natural Vision.
Wen, Haiguang.

Neural Encoding and Decoding with Deep Learning for Natural Vision. - 1 online resource (161 pages)

Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.

Thesis (Ph.D.)--Purdue University, 2018.

Includes bibliographical references

The overarching objective of this work is to bridge neuroscience and artificial intelligence to ultimately build machines that learn, act, and think like humans. In the context of vision, the brain enables humans to readily make sense of the visual world, e.g. recognizing visual objects. Developing human-like machines requires understanding the working principles underlying the human vision. In this dissertation, I ask how the brain encodes and represents dynamic visual information from the outside world, whether brain activity can be directly decoded to reconstruct and categorize what a person is seeing, and whether neuroscience theory can be applied to artificial models to advance computer vision. To address these questions, I used deep neural networks (DNN) to establish encoding and decoding models for describing the relationships between the brain and the visual stimuli. Using the DNN, the encoding models were able to predict the functional magnetic resonance imaging (fMRI) responses throughout the visual cortex given video stimuli; the decoding models were able to reconstruct and categorize the visual stimuli based on fMRI activity. To further advance the DNN model, I have implemented a new bidirectional and recurrent neural network based on the predictive coding theory. As a theory in neuroscience, predictive coding explains the interaction among feedforward, feedback, and recurrent connections. The results showed that this brain-inspired model significantly outperforms feedforward-only DNNs in object recognition. These studies have positive impact on understanding the neural computations under human vision and improving computer vision with the knowledge from neuroscience.

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

Mode of access: World Wide Web

ISBN: 9780438018075Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Neural Encoding and Decoding with Deep Learning for Natural Vision.
LDR:02943ntm a2200349Ki 4500 001 916679
005 20180927111921.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438018075
035 $a (MiAaPQ)AAI10792166
035 $a (MiAaPQ)purdue:22531
035 $a AAI10792166
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Wen, Haiguang. $3 1190487
245 1 0 $a Neural Encoding and Decoding with Deep Learning for Natural Vision.
264 0 $c 2018
300 $a 1 online resource (161 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: 79-10(E), Section: B.
500 $a Adviser: Zhongming Liu.
502 $a Thesis (Ph.D.)--Purdue University, 2018.
504 $a Includes bibliographical references
520 $a The overarching objective of this work is to bridge neuroscience and artificial intelligence to ultimately build machines that learn, act, and think like humans. In the context of vision, the brain enables humans to readily make sense of the visual world, e.g. recognizing visual objects. Developing human-like machines requires understanding the working principles underlying the human vision. In this dissertation, I ask how the brain encodes and represents dynamic visual information from the outside world, whether brain activity can be directly decoded to reconstruct and categorize what a person is seeing, and whether neuroscience theory can be applied to artificial models to advance computer vision. To address these questions, I used deep neural networks (DNN) to establish encoding and decoding models for describing the relationships between the brain and the visual stimuli. Using the DNN, the encoding models were able to predict the functional magnetic resonance imaging (fMRI) responses throughout the visual cortex given video stimuli; the decoding models were able to reconstruct and categorize the visual stimuli based on fMRI activity. To further advance the DNN model, I have implemented a new bidirectional and recurrent neural network based on the predictive coding theory. As a theory in neuroscience, predictive coding explains the interaction among feedforward, feedback, and recurrent connections. The results showed that this brain-inspired model significantly outperforms feedforward-only DNNs in object recognition. These studies have positive impact on understanding the neural computations under human vision and improving computer vision with the knowledge from neuroscience.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer science. $3 573171
650 4 $a Biomedical engineering. $3 588770
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0984
690 $a 0541
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Purdue University. $b Electrical and Computer Engineering. $3 1148521
773 0 $t Dissertation Abstracts International $g 79-10B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10792166 $z click for full text (PQDT)