scholarly journals PREVISÃO CLIMÁTICA DE PRECIPITAÇÃO PARA A REGIÃO SUL POR REDE NEURAL AUTOCONFIGURADA

2016 ◽  
Vol 38 ◽  
pp. 98
Author(s):  
Juliana Aparecida Anochi ◽  
Haroldo Fraga de Campos Velho
Keyword(s):  
Neural Network ◽  
Optimization Problem ◽  
Weather Forecasting ◽  
Meteorological Variable ◽  
Precipitation Forecast ◽  
Spatial And Temporal Variability ◽  
Strong Impact ◽  
Southern Brazil ◽  
Precipitation Field ◽  
The Neural Network

Climate prediction for precipitation field is a key issue, because such meteorological variable is the challenge for climate and weather forecasting due to the high spatial and temporal variability with strong impact on the society. A method based on the artificial neural network is applied to monthly and seasonal precipitation forecast in southern Brazil. The use of neural networks as a predictive model is widespread in different applications. The best configuration for the neural network is automatically calculated. The autoconfiguration scheme is described as an optimization problem.

scholarly journals Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Idris Kharroubi ◽  
Thomas Lim ◽  
Xavier Warin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Differential Equations ◽  
Numerical Experiments ◽  
Optimization Problem ◽  
Learning Approach ◽  
The Neural Network ◽  
Machine Learning Approach ◽  
Mesh Grid

AbstractWe study the approximation of backward stochastic differential equations (BSDEs for short) with a constraint on the gains process. We first discretize the constraint by applying a so-called facelift operator at times of a grid. We show that this discretely constrained BSDE converges to the continuously constrained one as the mesh grid converges to zero. We then focus on the approximation of the discretely constrained BSDE. For that we adopt a machine learning approach. We show that the facelift can be approximated by an optimization problem over a class of neural networks under constraints on the neural network and its derivative. We then derive an algorithm converging to the discretely constrained BSDE as the number of neurons goes to infinity. We end by numerical experiments.

Building Electronic Commerce Recommendation System Based on Ontology Learning and BP Neural Network

2013 ◽  
Vol 718-720 ◽  
pp. 1961-1966
Author(s):  
Hong Sheng Xu ◽  
Qing Tan
Keyword(s):  
Neural Network ◽  
Electronic Commerce ◽  
Bp Neural Network ◽  
Optimization Problem ◽  
Recommendation System ◽  
High Efficiency ◽  
Ontology Learning ◽  
The Neural Network ◽  
Network Process ◽  
Hidden Layer

Electronic commerce recommendation system can effectively retain user, prevent users from erosion, and improve e-commerce system sales. BP neural network using iterative operation, solving the weights of the neural network and close values to corresponding network process of learning and memory, to join the hidden layer nodes of the optimization problem of adjustable parameters increase. Ontology learning is the use of machine learning and statistical techniques, with automatic or semi-automatic way, from the existing data resources and obtaining desired body. The paper presents building electronic commerce recommendation system based on ontology learning and BP neural network. Experimental results show that the proposed algorithm has high efficiency.

A novel usage of neural network in optimization and implementation to the internal flow systems

2005 ◽  
Vol 77 (5) ◽  
pp. 369-375 ◽  
Author(s):  
Abdurrahman Hacioğlu
Keyword(s):  
Neural Network ◽  
Design Methodology ◽  
Optimization Problem ◽  
Internal Flow ◽  
Aerodynamic Design ◽  
Content Type ◽  
One Dimensional ◽  
Candidate Solution ◽  
The Neural Network ◽  
First Time

PurposeTo propose a robust and more effective algorithm for aerodynamic design optimization problem by using neural network.Design/methodology/approachNeural network and genetic algorithm (GA) are hybridized in a new way, and quasi one‐dimensional Euler equations are solved for internal flow in the nozzle.FindingsThe results indicate that the nozzle design can be performed successfully and quickly by using the implemented algorithm. It is observed that using the method decreased CFD solver calls about 21 and 46 per cent for transonic and supersonic flow, respectively.Originality/valueIt is the first time that the neural network is used for the candidate solution in the GA.

scholarly journals OPTIMIZATION OF EQUIPMENT RESERVE FOR INTELLECTUAL AUTOMATED SYSTEMS

2021 ◽  
Vol 2 (14) ◽  
pp. 87-99
Author(s):  
Vitaliy Chubaievskyi ◽  
Valery Lakhno ◽  
Berik Akhmetov ◽  
Olena Kryvoruchko ◽  
Dmytro Kasatkin ◽  
...  
Keyword(s):  
Neural Network ◽  
Control Systems ◽  
Optimization Problem ◽  
Destructive Interference ◽  
Network Analyzer ◽  
Calculation Methods ◽  
Automated Control ◽  
The Neural Network ◽  
The Cost ◽  
Selection Of

Algorithms for a neural network analyzer involved in the decision support system (DSS) during the selection of the composition of backup equipment (CBE) for intelligent automated control systems Smart City are proposed. A model, algorithms and software have been developed for solving the optimization problem of choosing a CBE capable of ensuring the uninterrupted operation of the IACS both in conditions of technological failures and in conditions of destructive interference in the operation of the IACS by the attackers. The proposed solutions help to reduce the cost of determining the optimal CBE for IACS by 15–17% in comparison with the results of known calculation methods. The results of computational experiments to study the degree of influence of the outputs of the neural network analyzer on the efficiency of the functioning of the CBE for IACS are presented.

scholarly journals Improved detection of far-side solar active regions using deep learning

2019 ◽  
Vol 632 ◽  
pp. A82
Author(s):  
T. Felipe ◽  
A. Asensio Ramos
Keyword(s):  
Neural Network ◽  
Space Weather ◽  
Weather Forecasting ◽  
Solar Rotation ◽  
Signal To Noise Ratio ◽  
Active Regions ◽  
Space Weather Forecasting ◽  
Solar Observations ◽  
The Neural Network ◽  
Cycle 24

Context. The analysis of waves on the visible side of the Sun allows the detection of active regions on the far side through local helioseismology techniques. Knowing the magnetism in the whole Sun, including the non-visible hemisphere, is fundamental for several space weather forecasting applications. Aims. Seismic identification of far-side active regions is challenged by the reduced signal-to-noise ratio, and only large and strong active regions can be reliable detected. Here we develop a new method to improve the identification of active region signatures in far-side seismic maps. Methods. We constructed a deep neural network that associates the far-side seismic maps obtained from helioseismic holography with the probability that active regions lie on the far side. The network was trained with pairs of helioseismic phase-shift maps and Helioseismic and Magnetic Imager (HMI) magnetograms acquired half a solar rotation later, which were used as a proxy for the presence of active regions on the far side. The method was validated using a set of artificial data, and it was also applied to actual solar observations during the period of minimum activity of solar cycle 24. Results. Our approach shows a higher sensitivity to the presence of far-side active regions than standard methods that have been applied up to date. The neural network can significantly increase the number of detected far-side active regions, and will potentially improve the application of far-side seismology to space weather forecasting.

scholarly journals A homotopy training algorithm for fully connected neural networks

2019 ◽  
Vol 475 (2231) ◽  
pp. 20190662
Author(s):  
Qipin Chen ◽  
Wenrui Hao
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Optimization Problem ◽  
Global Minimum ◽  
Optimization Problems ◽  
Continuous Path ◽  
Training Algorithm ◽  
Test Dataset ◽  
The Neural Network ◽  
Fully Connected

In this paper, we present a homotopy training algorithm (HTA) to solve optimization problems arising from fully connected neural networks with complicated structures. The HTA dynamically builds the neural network starting from a simplified version and ending with the fully connected network via adding layers and nodes adaptively. Therefore, the corresponding optimization problem is easy to solve at the beginning and connects to the original model via a continuous path guided by the HTA, which provides a high probability of obtaining a global minimum. By gradually increasing the complexity of the model along the continuous path, the HTA provides a rather good solution to the original loss function. This is confirmed by various numerical results including VGG models on CIFAR-10. For example, on the VGG13 model with batch normalization, HTA reduces the error rate by 11.86% on the test dataset compared with the traditional method. Moreover, the HTA also allows us to find the optimal structure for a fully connected neural network by building the neutral network adaptively.

Optimal Placement of Sensors to Detect Delamination in Composite Beams

1995 ◽  
Vol 48 (11S) ◽  
pp. S158-S167
Author(s):  
P. Hajela ◽  
Y. Teboub
Keyword(s):  
Neural Network ◽  
Optimization Problem ◽  
Matrix Cracking ◽  
Optimal Placement ◽  
Fiber Breakage ◽  
Strain Measurements ◽  
Integer Variables ◽  
The Neural Network ◽  
Search Tool ◽  
Trained Neural Network

The paper describes an approach for the optimal placement of sensors in composite beam structures for online detection of damage. The ability to identify damage is based on establishing a mapping between the charactgeristics of specific damage mechanisms (location and extent) such as delamination, fiber breakage, and matrix cracking, and strain measurements at the selected sensor locations; a trained neural network is proposed as a tool to generate this mapping. The design problem considered in the present paper was to place the least number of sensors in the structure so that the ability of the neural network to predict the extent and location of damage is not compromised. The optimization problem involved a mix of discrete and integer variables, and a genetic algorithm was used as the search tool.

Concept Optimization Model with Multilevel Hierarchy Based on Fuzzy Neural Network

2011 ◽  
Vol 338 ◽  
pp. 30-33
Author(s):  
Rui Feng Bo
Keyword(s):  
Neural Network ◽  
Optimization Problem ◽  
Function Analysis ◽  
Evaluation Model ◽  
Data Sets ◽  
The Neural Network ◽  
Concept Evaluation ◽  
Fuzzy Neural ◽  
Bottle Neck ◽  
Objective System

To implement optimization for mechanical concepts acquired by function analysis more effectively, BP neural network is adopted to structure multilevel evaluation model, which capitalizes on the features of nonlinearity, self-organization, and fault tolerance of neural network. By using appropriate data sets to train the neural network, expertise is acquired and expressed using a trained weight and threshold matrix. Once evaluation objectives of each candidate are fuzzily quantified, converted into evaluation attribute value, and fed into the trained network model, the optimal concept can be obtained. During the process, neural network is used to solve the bottle-neck problem of knowledge acquisition and expression and can be viewed as knowledge base and reasoning engine for the optimization. Hence the proposed evaluation model can effectively deal with concept evaluation and optimization problem with multilevel objective system.

Sign in / Sign up

Export Citation Format

Share Document