scholarly journals Training Images-Based Stochastic Simulation on Many-Core Architectures

10.5772/64276 ◽  
2016 ◽  
Author(s):  
Tao Huang ◽  
Detang Lu
Keyword(s):  
Stochastic Simulation ◽  
Training Images ◽  
Many Core

Fast wavelet-based stochastic simulation using training images

2015 ◽  
Vol 20 (3) ◽  
pp. 399-420 ◽  
Author(s):  
Snehamoy Chatterjee ◽  
Hussein Mustapha ◽  
Roussos Dimitrakopoulos
Keyword(s):  
Stochastic Simulation ◽  
Training Images ◽  
Fast Wavelet

Stochastic simulation of patterns using ISOMAP for dimensionality reduction of training images

2015 ◽  
Vol 79 ◽  
pp. 82-93 ◽  
Author(s):  
Ting Zhang ◽  
Yi Du ◽  
Tao Huang ◽  
Jiaqing Yang ◽  
Xue Li
Keyword(s):  
Dimensionality Reduction ◽  
Stochastic Simulation ◽  
Training Images

Stochastic simulation of cell cycle

2012 ◽  
Vol 1 (1) ◽  
Author(s):  
P. Luvsantseren ◽  
K. Lochin ◽  
E. Purevjav
Keyword(s):  
Cell Cycle ◽  
Stochastic Simulation

Architecture and Evaluation of Low Power Many-Core SoC with Two 32-Core Clusters

2014 ◽  
Vol E97.C (4) ◽  
pp. 360-368
Author(s):  
Takashi MIYAMORI ◽  
Hui XU ◽  
Hiroyuki USUI ◽  
Soichiro HOSODA ◽  
Toru SANO ◽  
...  
Keyword(s):  
Low Power ◽  
Many Core

CNN performance dependence on linear image processing

2020 ◽  
Vol 2020 (10) ◽  
pp. 310-1-310-7
Author(s):  
Khalid Omer ◽  
Luca Caucci ◽  
Meredith Kupinski
Keyword(s):  
Image Processing ◽  
Texture Classification ◽  
Full Rank ◽  
Detection Performance ◽  
Ideal Observer ◽  
Training Data ◽  
Image Texture ◽  
Training Images ◽  
Analytic Expressions ◽  
Linear Compression

This work reports on convolutional neural network (CNN) performance on an image texture classification task as a function of linear image processing and number of training images. Detection performance of single and multi-layer CNNs (sCNN/mCNN) are compared to optimal observers. Performance is quantified by the area under the receiver operating characteristic (ROC) curve, also known as the AUC. For perfect detection AUC = 1.0 and AUC = 0.5 for guessing. The Ideal Observer (IO) maximizes AUC but is prohibitive in practice because it depends on high-dimensional image likelihoods. The IO performance is invariant to any fullrank, invertible linear image processing. This work demonstrates the existence of full-rank, invertible linear transforms that can degrade both sCNN and mCNN even in the limit of large quantities of training data. A subsequent invertible linear transform changes the images’ correlation structure again and can improve this AUC. Stationary textures sampled from zero mean and unequal covariance Gaussian distributions allow closed-form analytic expressions for the IO and optimal linear compression. Linear compression is a mitigation technique for high-dimension low sample size (HDLSS) applications. By definition, compression strictly decreases or maintains IO detection performance. For small quantities of training data, linear image compression prior to the sCNN architecture can increase AUC from 0.56 to 0.93. Results indicate an optimal compression ratio for CNN based on task difficulty, compression method, and number of training images.

On Synchronization and Evaluation Method of Chipped Many-Core Processor

2010 ◽  
Vol 33 (10) ◽  
pp. 1777-1787 ◽  
Author(s):  
Wei-Zhi XU ◽  
Feng-Long SONG ◽  
Zhi-Yong LIU ◽  
Dong-Rui FAN ◽  
Lei YU ◽  
...  
Keyword(s):  
Evaluation Method ◽  
Many Core

Using Write Mask to Support Hybrid Write-Back and Write-Through Cache Policy on Many-Core Architectures

2009 ◽  
Vol 31 (11) ◽  
pp. 1918-1928 ◽  
Author(s):  
Wei LIN ◽  
Xiao-Chun YE ◽  
Feng-Long SONG ◽  
Hao ZHANG
Keyword(s):  
Many Core
Sign in / Sign up

Export Citation Format

Share Document