.png){kind=icon}
返回
Novel Preprocessors for Convolution Neural Networks
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2022.3163405.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Fooling neural networks is a main concern in the process of Artificial Intelligence optimization. Character perturbation make part of a text unnoticeable for some systems, even for human observers. This research focuses the probe on a novel input preprocessing technique, which applies with the Convolutional Neural Networks for character recognition applications. Using Hand-written, Font, and Arabic Alphabet datasets, we show the CNN competitive results in classification. Then, we apply random deformation by mean of reshaping and relocation on the three testing datasets. As a reaction to change, the CNN demonstrates a confused behavior. Therefore, we design a Weightless Neural Network preprocessor that optimizes the shapes of deformed characters. Finally, we compare the impact of corrected input in improving the CNN performance. To measure the success of our preprocessor, we have applied it on well-known CNNs to compare the results between defected and rectified test datasets. Using Keras, we reconstructed LeNet-5, AlexNet and ZFNet for testing. Then, we conduct the test on the three databases to show how the recognition capability of CNNs would decline, then improve after preprocessing.
Keyword:
Convolutional neural networks
Training
Data preprocessing
Testing
Shape
Random access memory
Robots
Artificial neural networks
logic-based intelligence
pattern recognition
preprocessor
weightless neural networks
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Understanding adversarial training: Increasing local stability of supervised models through robust optimization.png)
NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Solvent-mediated supramolecular templated assembly of a metal organophosphonate via a crystal–amorphous–crystal transformationCrystEngComm
CrystEngCommIF0
PREAI
分享收藏分享收藏Reactivation or transformation? Motor memory consolidation associated with cerebral activation time-locked to sleep spindlesPLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容