Global Optimisation of Neural Networks Using a Deterministic Hybrid Approach

2002 ◽  
pp. 79-92 ◽  
Author(s):  
Gleb Beliakov ◽  
Ajith Abraham
Keyword(s):  
Neural Networks ◽  
Hybrid Approach ◽  
Global Optimisation

Hybrid Approach and Architecture to Detect Fake News on Twitter in Real-Time using Neural Networks

2020 ◽  
Author(s):  
Madusha Prasanjith Thilakarathna ◽  
Vihanga Ashinsana Wijayasekara ◽  
Yasiru Gamage ◽  
Kavindi Hanshani Peiris ◽  
Chanuka Abeysinghe ◽  
...  
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Hybrid Approach ◽  
Fake News

scholarly journals Hybrid Neural-global Minimization Method of Logical Rule Extraction

1999 ◽  
Vol 3 (5) ◽  
pp. 348-356 ◽  
Author(s):  
Wlodzislaw Duch ◽  
◽  
Rafal Adamczak ◽  
KrzysAof Grabczewski ◽  
Grzegorz Zal
Keyword(s):  
Neural Networks ◽  
Hybrid Approach ◽  
Real Life ◽  
Rule Extraction ◽  
Global Minimization ◽  
Minimization Method ◽  
Life Problems ◽  
Multilayered Perceptron ◽  
Logical Functions ◽  
Logical Rules

Methodology of extraction of optimal sets of logical rules using neural networks and global minimization procedures has been developed. Initial rules are extracted using density estimation neural networks with rectangular functions or multilayered perceptron (MLP) networks trained with constrained backpropagation algorithm, transforming MLPs into simpler networks performing logical functions. A constructive algorithm called CMLP2LN is proposed, in which rules of increasing specificity are generated consecutively by adding more nodes to the network. Neural rule extraction is followed by optimization of rules using global minimization techniques. Estimation of confidence of various sets of rules is discussed. The hybrid approach to rule extraction has been applied to a number of benchmark and real life problems with very good results.

A Hybrid Approach Based on Self-Organizing Neural Networks and the K-Nearest Neighbors Method to Study Molecular Similarity

2011 ◽  
Vol 1 (1) ◽  
pp. 75-95 ◽  
Author(s):  
Abdelmalek Amine ◽  
Zakaria Elberrichi ◽  
Michel Simonet ◽  
Ali Rahmouni
Keyword(s):  
Neural Networks ◽  
Molecular Similarity ◽  
Learning Algorithm ◽  
Hybrid Approach ◽  
Structural Similarity ◽  
Biological Properties ◽  
Learning Tools ◽  
K Nearest Neighbors ◽  
Virtual Chemical Libraries ◽  
Self Organizing

The “Molecular Similarity Principle” states that structurally similar molecules tend to have similar properties—physicochemical and biological. The question then is how to define “structural similarity” algorithmically and confirm its usefulness. Within this framework, research by similarity is registered, which is a practical approach to identify molecule candidates (to become drugs or medicines) from databases or virtual chemical libraries by comparing the compounds two by two. Many statistical models and learning tools have been developed to correlate the molecules’ structure with their chemical, physical or biological properties. The role of data mining in chemistry is to evaluate “hidden” information in a set of chemical data. Each molecule is represented by a vector of great dimension (using molecular descriptors), the applying a learning algorithm on these vectors. In this paper, the authors study the molecular similarity using a hybrid approach based on Self-Organizing Neural Networks and Knn Method.

scholarly journals Using Convolutional Neural Networks to Automate Aircraft Maintenance Visual Inspection

Aerospace ◽  
2020 ◽  
Vol 7 (12) ◽  
pp. 171
Author(s):  
Anil Doğru ◽  
Soufiane Bouarfa ◽  
Ridwan Arizar ◽  
Reyhan Aydoğan
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Visual Inspection ◽  
Hybrid Approach ◽  
Lightning Strike ◽  
Aircraft Maintenance ◽  
Original Dataset ◽  
Wide Range ◽  
Augmentation Techniques

Convolutional Neural Networks combined with autonomous drones are increasingly seen as enablers of partially automating the aircraft maintenance visual inspection process. Such an innovative concept can have a significant impact on aircraft operations. Though supporting aircraft maintenance engineers detect and classify a wide range of defects, the time spent on inspection can significantly be reduced. Examples of defects that can be automatically detected include aircraft dents, paint defects, cracks and holes, and lightning strike damage. Additionally, this concept could also increase the accuracy of damage detection and reduce the number of aircraft inspection incidents related to human factors like fatigue and time pressure. In our previous work, we have applied a recent Convolutional Neural Network architecture known by MASK R-CNN to detect aircraft dents. MASK-RCNN was chosen because it enables the detection of multiple objects in an image while simultaneously generating a segmentation mask for each instance. The previously obtained F1 and F2 scores were 62.67% and 59.35%, respectively. This paper extends the previous work by applying different techniques to improve and evaluate prediction performance experimentally. The approach uses include (1) Balancing the original dataset by adding images without dents; (2) Increasing data homogeneity by focusing on wing images only; (3) Exploring the potential of three augmentation techniques in improving model performance namely flipping, rotating, and blurring; and (4) using a pre-classifier in combination with MASK R-CNN. The results show that a hybrid approach combining MASK R-CNN and augmentation techniques leads to an improved performance with an F1 score of (67.50%) and F2 score of (66.37%).

scholarly journals SAR Image Despeckling by Deep Neural Networks: from a Pre-Trained Model to an End-to-End Training Strategy

2020 ◽  
Vol 12 (16) ◽  
pp. 2636
Author(s):  
Emanuele Dalsasso ◽  
Xiangli Yang ◽  
Loïc Denis ◽  
Florence Tupin ◽  
Wen Yang
Keyword(s):  
Neural Networks ◽  
Gaussian Noise ◽  
State Of The Art ◽  
Additive White Gaussian Noise ◽  
Hybrid Approach ◽  
White Gaussian Noise ◽  
Training Data ◽  
Speckle Reduction ◽  
Sar Image ◽  
Sar Images

Speckle reduction is a longstanding topic in synthetic aperture radar (SAR) images. Many different schemes have been proposed for the restoration of intensity SAR images. Among the different possible approaches, methods based on convolutional neural networks (CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. CNN training requires good training data: many pairs of speckle-free/speckle-corrupted images. This is an issue in SAR applications, given the inherent scarcity of speckle-free images. To handle this problem, this paper analyzes different strategies one can adopt, depending on the speckle removal task one wishes to perform and the availability of multitemporal stacks of SAR data. The first strategy applies a CNN model, trained to remove additive white Gaussian noise from natural images, to a recently proposed SAR speckle removal framework: MuLoG (MUlti-channel LOgarithm with Gaussian denoising). No training on SAR images is performed, the network is readily applied to speckle reduction tasks. The second strategy considers a novel approach to construct a reliable dataset of speckle-free SAR images necessary to train a CNN model. Finally, a hybrid approach is also analyzed: the CNN used to remove additive white Gaussian noise is trained on speckle-free SAR images. The proposed methods are compared to other state-of-the-art speckle removal filters, to evaluate the quality of denoising and to discuss the pros and cons of the different strategies. Along with the paper, we make available the weights of the trained network to allow its usage by other researchers.

Sign in / Sign up

Export Citation Format

Share Document