語系:
繁體中文
English
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
Hardware Implementation of Neural Ne...
~
Gupta, Tushar.
FindBook
Google Book
Amazon
博客來
Hardware Implementation of Neural Network for Image Classification.
紀錄類型:
書目-電子資源 : Monograph/item
正題名/作者:
Hardware Implementation of Neural Network for Image Classification./
作者:
Gupta, Tushar.
出版者:
Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:
56 p.
附註:
Source: Masters Abstracts International, Volume: 82-04.
Contained By:
Masters Abstracts International82-04.
標題:
Electrical engineering. -
電子資源:
https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28090965
ISBN:
9798672197760
Hardware Implementation of Neural Network for Image Classification.
Gupta, Tushar.
Hardware Implementation of Neural Network for Image Classification.
- Ann Arbor : ProQuest Dissertations & Theses, 2020 - 56 p.
Source: Masters Abstracts International, Volume: 82-04.
Thesis (M.S.)--State University of New York at Buffalo, 2020.
This item must not be sold to any third party vendors.
Image Classification has been the topic of research for long time due to its wide range of applications which includes vehicle license plate recognition, text recognition, medical diagnosis and the list goes on. Traditional computer vision approaches can become inefficient as the number of classes to classify increase. It also has a plethora of feature parameter which becomes an overhead. Machine learning algorithms can be utilized to utilized to discover the underlying patterns in classes of images.This work aims at developing hardware for image classification. Neural Network has been modeled to classify the USPS dataset consisting of handwritten digit (0-9) images with 16x16 grayscale pixels as input features. First the neural network is trained using 8800 of these images and then tested with 2200 images. After achieving the promising results on MATLAB circuit was designed using 65 nm MOS switched capacitors. The circuit consists of input layer, hidden layer and the output layer. After simulating the circuit on cadence virtuoso we achieved 88% accuracy.
ISBN: 9798672197760Subjects--Topical Terms:
649834
Electrical engineering.
Subjects--Index Terms:
Handwritten digits classification
Hardware Implementation of Neural Network for Image Classification.
LDR
:02464nmm a2200457 4500
001
2279607
005
20210823080256.5
008
220723s2020 ||||||||||||||||| ||eng d
020
$a
9798672197760
035
$a
(MiAaPQ)AAI28090965
035
$a
AAI28090965
040
$a
MiAaPQ
$c
MiAaPQ
100
1
$a
Gupta, Tushar.
$3
3178512
245
1 0
$a
Hardware Implementation of Neural Network for Image Classification.
260
1
$a
Ann Arbor :
$b
ProQuest Dissertations & Theses,
$c
2020
300
$a
56 p.
500
$a
Source: Masters Abstracts International, Volume: 82-04.
500
$a
Advisor: Sanyal, Arindam.
502
$a
Thesis (M.S.)--State University of New York at Buffalo, 2020.
506
$a
This item must not be sold to any third party vendors.
520
$a
Image Classification has been the topic of research for long time due to its wide range of applications which includes vehicle license plate recognition, text recognition, medical diagnosis and the list goes on. Traditional computer vision approaches can become inefficient as the number of classes to classify increase. It also has a plethora of feature parameter which becomes an overhead. Machine learning algorithms can be utilized to utilized to discover the underlying patterns in classes of images.This work aims at developing hardware for image classification. Neural Network has been modeled to classify the USPS dataset consisting of handwritten digit (0-9) images with 16x16 grayscale pixels as input features. First the neural network is trained using 8800 of these images and then tested with 2200 images. After achieving the promising results on MATLAB circuit was designed using 65 nm MOS switched capacitors. The circuit consists of input layer, hidden layer and the output layer. After simulating the circuit on cadence virtuoso we achieved 88% accuracy.
590
$a
School code: 0656.
650
4
$a
Electrical engineering.
$3
649834
650
4
$a
Computer science.
$3
523869
650
4
$a
Medical imaging.
$3
3172799
650
4
$a
Information technology.
$3
532993
653
$a
Handwritten digits classification
653
$a
Image classification
653
$a
Machine learning
653
$a
Neural network
653
$a
Switched capacitor
653
$a
USPS
653
$a
Vehicle license plate recognition
653
$a
Text recognition
653
$a
Medical diagnosis
653
$a
Computer vision
653
$a
Hardware development
690
$a
0544
690
$a
0984
690
$a
0489
690
$a
0574
710
2
$a
State University of New York at Buffalo.
$b
Electrical Engineering.
$3
1019366
773
0
$t
Masters Abstracts International
$g
82-04.
790
$a
0656
791
$a
M.S.
792
$a
2020
793
$a
English
856
4 0
$u
https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28090965
筆 0 讀者評論
館藏地:
全部
電子資源
出版年:
卷號:
館藏
1 筆 • 頁數 1 •
1
條碼號
典藏地名稱
館藏流通類別
資料類型
索書號
使用類型
借閱狀態
預約狀態
備註欄
附件
W9431340
電子資源
11.線上閱覽_V
電子書
EB
一般使用(Normal)
在架
0
1 筆 • 頁數 1 •
1
多媒體
評論
新增評論
分享你的心得
Export
取書館
處理中
...
變更密碼
登入