東華大學圖書館 |

語系: 繁體中文

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

Sparse coding and compressed sensing...

Hahn, William Edward.

FindBook

Google Book

Amazon

博客來

Sparse coding and compressed sensing: Locally competitive algorithms and random projections.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Sparse coding and compressed sensing: Locally competitive algorithms and random projections./
作者:	Hahn, William Edward.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2016,
面頁冊數:	288 p.
附註:	Source: Dissertations Abstracts International, Volume: 78-06, Section: B.
Contained By:	Dissertations Abstracts International78-06B.
標題:	Neurosciences. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10300346
ISBN:	9781369423853

Sparse coding and compressed sensing: Locally competitive algorithms and random projections.
Hahn, William Edward.

Sparse coding and compressed sensing: Locally competitive algorithms and random projections. - Ann Arbor : ProQuest Dissertations & Theses, 2016 - 288 p.

Source: Dissertations Abstracts International, Volume: 78-06, Section: B.

Thesis (Ph.D.)--Florida Atlantic University, 2016.

This item must not be added to any third party search indexes.

For an 8-bit grayscale image patch of size n x n, the number of distinguishable signals is 256(n 2). Natural images (e.g.,photographs of a natural scene) comprise a very small subset of these possible signals. Traditional image and video processing relies on band-limited or low-pass signal models. In contrast, we will explore the observation that most signals of interest are sparse, i.e. in a particular basis most of the expansion coefficients will be zero. Recent developments in sparse modeling and L1 optimization have allowed for extraordinary applications such as the single pixel camera, as well as computer vision systems that can exceed human performance. Here we present a novel neural network architecture combining a sparse filter model and locally competitive algorithms (LCAs), and demonstrate the networks ability to classify human actions from video. Sparse filtering is an unsupervised feature learning algorithm designed to optimize the sparsity of the feature distribution directly without having the need to model the data distribution. LCAs are defined by a system of differential equations where the initial conditions define an optimization problem and the dynamics converge to a sparse decomposition of the input vector. We applied this architecture to train a classifier on categories of motion in human action videos. Inputs to the network were small 3D patches taken from frame differences in the videos. Dictionaries were derived for each action class and then activation levels for each dictionary were assessed during reconstruction of a novel test patch. We discuss how this sparse modeling approach provides a natural framework for multi-sensory and multimodal data processing including RGB video, RGBD video, hyper-spectral video, and stereo audio/video streams.

ISBN: 9781369423853Subjects--Topical Terms:

588700
Neurosciences.

Sparse coding and compressed sensing: Locally competitive algorithms and random projections.
LDR:02943nmm a2200337 4500 001 2206795
005 20190906083220.5
008 201008s2016 ||||||||||||||||| ||eng d
020 $a 9781369423853
035 $a (MiAaPQ)AAI10300346
035 $a AAI10300346
040 $a MiAaPQ $c MiAaPQ
100 1 $a Hahn, William Edward. $3 3433712
245 1 0 $a Sparse coding and compressed sensing: Locally competitive algorithms and random projections.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2016
300 $a 288 p.
500 $a Source: Dissertations Abstracts International, Volume: 78-06, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Barenholtz, Elan.
502 $a Thesis (Ph.D.)--Florida Atlantic University, 2016.
506 $a This item must not be added to any third party search indexes.
506 $a This item must not be sold to any third party vendors.
520 $a For an 8-bit grayscale image patch of size n x n, the number of distinguishable signals is 256(n 2). Natural images (e.g.,photographs of a natural scene) comprise a very small subset of these possible signals. Traditional image and video processing relies on band-limited or low-pass signal models. In contrast, we will explore the observation that most signals of interest are sparse, i.e. in a particular basis most of the expansion coefficients will be zero. Recent developments in sparse modeling and L1 optimization have allowed for extraordinary applications such as the single pixel camera, as well as computer vision systems that can exceed human performance. Here we present a novel neural network architecture combining a sparse filter model and locally competitive algorithms (LCAs), and demonstrate the networks ability to classify human actions from video. Sparse filtering is an unsupervised feature learning algorithm designed to optimize the sparsity of the feature distribution directly without having the need to model the data distribution. LCAs are defined by a system of differential equations where the initial conditions define an optimization problem and the dynamics converge to a sparse decomposition of the input vector. We applied this architecture to train a classifier on categories of motion in human action videos. Inputs to the network were small 3D patches taken from frame differences in the videos. Dictionaries were derived for each action class and then activation levels for each dictionary were assessed during reconstruction of a novel test patch. We discuss how this sparse modeling approach provides a natural framework for multi-sensory and multimodal data processing including RGB video, RGBD video, hyper-spectral video, and stereo audio/video streams.
590 $a School code: 0119.
650 4 $a Neurosciences. $3 588700
650 4 $a Applied Mathematics. $3 1669109
650 4 $a Computer science. $3 523869
690 $a 0317
690 $a 0364
690 $a 0984
710 2 $a Florida Atlantic University. $3 1017837
773 0 $t Dissertations Abstracts International $g 78-06B.
790 $a 0119
791 $a Ph.D.
792 $a 2016
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10300346