Computational Intelligence

Context: Multiple types of processing units (e.g., CPUs, GPUs and FPGAs) can be used jointly to achieve better performance in computational systems. However, these units are built with fundamentally different characteristics and demand attention especially towards software deployment. 

Categories:
142 Views

 # of original news:30;
# of candidate news:25899;
# of reprinted news (no source label):4234 (537)

 

Categories:
218 Views

The whole data set will be published after the acceptance of our paper via the same url as shown in the paper.

 

When using PackageRank software to analyze our data set, please do not change the name of the .net files.

 

The .net file has the following format:

Node count: *Vertices count

 

Node List:

    number "node name"

EX:   1    "org.apache.tools.ant.taskdefs.optional.sitraka"

 

Arc List:

node1 node2 weight

EX: 1 2 3

Meaning: from node 1 to node 2 with weight 3

 

Categories:
182 Views

Computational modelling of metabolic processes has proven to be a useful approach to formulate our knowledge and improve our understanding of core biochemical systems that are crucial to maintain cellular functions. Recently, it has become evident that metabolism is not only responsible for generating the required energy and controlling the abundance of metabolites within a cell, but also has an important role in and influence on cellular fate specification.

Categories:
448 Views

We provide results of "Robust Visual Tracking Based on Adaptive Extraction and Enhancement of Correlation Filter" on OTB2015 dataset, including the results of proposed tracker with HOG, HOGCN, and deep CNN features.

Categories:
348 Views

Vibration data collected from handpump handles in Kwale, Kenya.

Categories:
1244 Views

800x600

Normal
0

7.8 磅
0
2

false
false
false

EN-US
ZH-CN
X-NONE

MicrosoftInternetExplorer4

Categories:
138 Views

D U C 2 0 0 2 dataset (https://www-nlpir.nist.gov/projects/duc/guidelines/2002.html) processed through doc2vec (https://github.com/jhlau/doc2vec)
This dataset includes the documents embeddings of the full DUC 2002 in the following configurations:

Categories:
841 Views

Our dataset includes three parts: MNIST-rot,  MNIST-scale, and MNIST-rand.
MNIST-rot is generated by randomly rotating
each sample in the MNIST testing dataset in $[0,2\pi]$.
We generated MNIST-scale by randomly scaling
the ratio of the area occupied by the symbol over that of the entire image by a factor
in $[0.5,1]$, and generated MNIST-rand by scaling and
rotating images in MNIST testing dataset simultaneously.

Categories:
822 Views

Deep learning belongs to the scope of artificial intelligence, which has attracted researchers all over the world. The CNN is one the most popular techniques of deep learning. In this paper, the WLAN (wireless local area network) localization is given by SVD (singular value decomposition) noise-reduction and CNN (convolutional neural network).

Categories:
395 Views

Pages