S. Maslov’s iterative method: 15 years later (freedom of Choice, neural networks, numerical optimization, uncertainty reasoning, and chemical computing)

1996 ◽  
pp. 175-189 ◽  
Author(s):  
V. Kreinovich
Keyword(s):  
Neural Networks ◽  
Iterative Method ◽  
Numerical Optimization ◽  
Freedom Of Choice ◽  
Uncertainty Reasoning

Methods for Multi-Step Time Series Forecasting Neural Networks

2011 ◽  
pp. 226-250 ◽  
Author(s):  
Douglas M. Kline
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Iterative Method ◽  
Time Series Forecasting ◽  
Independent Method ◽  
Data Series ◽  
Operating Characteristics ◽  
Quarterly Data ◽  
Joint Method

In this study, we examine two methods for Multi-Step forecasting with neural networks: the Joint Method and the Independent Method. A subset of the M-3 Competition quarterly data series is used for the study. The methods are compared to each other, to a neural network Iterative Method, and to a baseline de-trended de-seasonalized naïve forecast. The operating characteristics of the three methods are also examined. Our findings suggest that for longer forecast horizons the Joint Method performs better, while for short forecast horizons the Independent Method performs better. In addition, the Independent Method always performed at least as well as or better than the baseline naïve and neural network Iterative Methods.

Approximation Performance of BP Neural Networks Improved by Heuristic Approach

2013 ◽  
Vol 411-414 ◽  
pp. 1952-1955 ◽  
Author(s):  
Shuo Ding ◽  
Xiao Heng Chang ◽  
Qing Hui Wu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Numerical Optimization ◽  
Heuristic Algorithms ◽  
Nonlinear Function ◽  
Heuristic Approach ◽  
Optimization Approach ◽  
Bp Neural Networks ◽  
The One

Among all improved BP neural network algorithms, the one improved by heuristic approach is studied in this paper. Firstly, three types of improved heuristic algorithms of BP neural network are programmed in the environment of MATLAB7.0. Then network training and simulation test are conducted taking a nonlinear function as an example. The approximation performances of BP neural networks improved by different numerical optimization approaches are compared to aid the selection of proper numerical optimization approach.

scholarly journals What is this fruit? Neural network application for Vietnamese fruit recognition

2018 ◽  
Vol 20 ◽  
pp. 02009 ◽  
Author(s):  
Mateusz Baryła
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Information Theory ◽  
Deep Learning ◽  
Numerical Optimization ◽  
Web Application ◽  
Short Description ◽  
Network Application ◽  
Key Features ◽  
Probability Information

We use deep learning for problems in computer vision, image recognition and classification. Deep learning methods for fruit recognition are built with methods where features (in our case fruits key features) are processed and sent through multiple layers where transformations and computations are done sequentially to form a prediction model. Deep learning algorithms draws inspiration from many fields especially applied maths fundamentals like linear algebra, probability, information theory and numerical optimization. To the best of our knowledge this is the first web application for fruit recognition. Thanks to that users will be able to recognize most of the Vietnamese fruits without knowledge of Vietnamese language. What is more they can get a short description for each fruit and a video how to eat it. In the paper we compare different models of convolutional neural networks in order to find the best possible model of CNN. This system will is fine-tuned, what means that it learns on examples provided by users of application. Having that we propose algorithm which detects non-fruits pictures uploaded by user.

scholarly journals Simple Iterative Method for Generating Targeted Universal Adversarial Perturbations

Algorithms ◽  
2020 ◽  
Vol 13 (11) ◽  
pp. 268 ◽  
Author(s):  
Hokuto Hirano ◽  
Kazuhiro Takemoto
Keyword(s):  
Neural Networks ◽  
Iterative Method ◽  
Image Classification ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Specific Class ◽  
Targeted Attacks ◽  
Fast Gradient ◽  
Classification Tasks ◽  
Sign Method

Deep neural networks (DNNs) are vulnerable to adversarial attacks. In particular, a single perturbation known as the universal adversarial perturbation (UAP) can foil most classification tasks conducted by DNNs. Thus, different methods for generating UAPs are required to fully evaluate the vulnerability of DNNs. A realistic evaluation would be with cases that consider targeted attacks; wherein the generated UAP causes the DNN to classify an input into a specific class. However, the development of UAPs for targeted attacks has largely fallen behind that of UAPs for non-targeted attacks. Therefore, we propose a simple iterative method to generate UAPs for targeted attacks. Our method combines the simple iterative method for generating non-targeted UAPs and the fast gradient sign method for generating a targeted adversarial perturbation for an input. We applied the proposed method to state-of-the-art DNN models for image classification and proved the existence of almost imperceptible UAPs for targeted attacks; further, we demonstrated that such UAPs can be easily generated.

Shape From Shading: A Non-iterative Method Using Neural Networks

2021 ◽  
pp. 759-768
Author(s):  
Omar El Farouk Bourahla ◽  
Abderrahmane Mahdi Debbah ◽  
Lyes Abada ◽  
Saliha Aouat
Keyword(s):  
Neural Networks ◽  
Iterative Method ◽  
Shape From Shading

Numerical optimization and experimental research on listening environment of crew based on neural networks

2017 ◽  
Vol 220 ◽  
pp. 244-253
Author(s):  
He-xuan Hu ◽  
Bo Tang ◽  
Zheng-yin Ding ◽  
Chun-lai Shi ◽  
Bang-wen Shi ◽  
...  
Keyword(s):  
Neural Networks ◽  
Experimental Research ◽  
Numerical Optimization
Sign in / Sign up

Export Citation Format

Share Document