Generalization and the Backward Propagation Neural Network,

1988 ◽  
Author(s):  
Charles M. Bachmann
Keyword(s):  
Neural Network ◽  
Backward Propagation

scholarly journals A backward propagation neural network for predicting daily transpiration of poplar

2007 ◽  
Vol 50 (5) ◽  
pp. 1277-1284 ◽  
Author(s):  
Yan Meijun ◽  
Yang Peiling ◽  
Ren Shumei ◽  
Luo Yuanpei ◽  
Xu Tingwu
Keyword(s):  
Neural Network ◽  
Daily Transpiration ◽  
Backward Propagation

scholarly journals Traffic marking recognition based on generating antagonistic neural network

2019 ◽  
Vol 136 ◽  
pp. 04076 ◽  
Author(s):  
Shuwei Xu ◽  
Shan Zhang ◽  
Shuwei Xu
Keyword(s):  
Neural Network ◽  
Markov Chain ◽  
High Accuracy ◽  
Experimental Results ◽  
Detection Methods ◽  
Image Detection ◽  
Fast Recognition ◽  
Repeated Sampling ◽  
Backward Propagation ◽  
Traditional Image

This paper presents a method of extracting traffic lines from image images by GAN. Compared with the traditional image detection methods, the counter neural network does not need repeated sampling of Markov chain and adopts the method of backward propagation. Therefore, when detecting the image, GAN do not need to be updated with samples; it can produce better quality samples, express more clearly. Experimental results show that the method has strong generalization ability, fast recognition speed and high accuracy.

Applying BP Neural Network Model to Forecast the Largest Coiling Torque of down Coilers

2014 ◽  
Vol 936 ◽  
pp. 1614-1619
Author(s):  
Ke Zhao ◽  
Zhi Gang Wang ◽  
Chang Ming Liu
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
High Strength ◽  
Coiling Temperature ◽  
Strip Steel ◽  
Development And Utilization ◽  
Hot Rolling Mill ◽  
Bp Neural Network Model ◽  
Backward Propagation ◽  
Relationship Of

Down coiler is an important equipment of hot rolling mill. The coiling torque is changing constantly in the process of strip steel coiling, and the largest coiling torque depends on several factors, such as the material and specification of coiling strip, the coiling temperature and the process parameters and so on. Only when the largest coiling torque is less than the carrying capacity could the coiler work in security. A topology relationship of the largest coiling torque among the materials, the specification of the strip and the coiling temperature is established. Based on the BP(backward propagation of errors) artificial neural network, a predicted formula model of the largest coiling torque in coiling high strength strip is built, which provides a theoretical basis for the development and utilization of the largest working potential of the down coiler. Keywords: Down Coiler; BP Neural Network; Coiling Torque; Forecast

Prediction of Egg's Freshness Using Backward Propagation Neural Network

2011 ◽  
Vol 27 (2) ◽  
pp. 279-285 ◽  
Author(s):  
S. Dhakal ◽  
J. Wu ◽  
J. Chen ◽  
Y. Peng
Keyword(s):  
Neural Network ◽  
Backward Propagation

Prediction of Forming Load for the Helical Gear Precision Forging by BP Neural Network

2013 ◽  
Vol 823 ◽  
pp. 170-174
Author(s):  
Wei Feng ◽  
Ji Chang Cao ◽  
Shu Ting Wu ◽  
Yang Fan Li
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Fem Simulation ◽  
Helical Gear ◽  
The Finite Element Method ◽  
Forming Process ◽  
Forming Load ◽  
Precision Forging ◽  
Metal Forming Process ◽  
Backward Propagation

Precision forging of the helical gear is a complex metal forming process under coupled effects with multi-factors. The high forming load is required to fill the teeth corner, which significantly causes failure, plastic deformation and wear of dies. The maximum forming load during precision forging helical gear is calculated by the finite element method (FEM). Combining the FEM simulation results with the artificial neural networks (ANN), backward propagation (BP) neural network is trained using the data of FEM simulation as learning sample. The trained BP neural network is validated using test samples and used to predict the maximum forming load under the different deformation conditions. The results show that the predicted results agree well with the simulated ones, the differences of prediction results exhibit low value, the predicted precision satisfy the request of industry.

scholarly journals Expression Analysis System

2021 ◽  
Vol 10 (3) ◽  
pp. 13-15
Author(s):  
Riya KalburgI ◽  
Punit Solanki ◽  
Rounak Suthar ◽  
Saurabh Suman
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Personality Traits ◽  
Facial Expressions ◽  
Network Algorithms ◽  
Periodic Monitoring ◽  
Derivative System ◽  
Analysis System ◽  
The Individual ◽  
Backward Propagation

Expression is the most basic personality trait of an individual. Expressions, ubiquitous to humans from all cultures, can be pivotal in analyzing the personality which is not confined to boundaries. Analyzing the changes in the expression of the individual can bolster the process of deriving his/her personality traits underscoring the paramount reactions like anger, happiness, sadness and so on. This paper aims to exercise Neural Network algorithms to predict the personality traits of an individual from his/her facial expressions. In this paper, a methodology to analyze the personality traits of the individual by periodic monitoring of the changes in facial expressions is presented. The proposed system is intended to analyze the expressions by exploiting Neural Networks strategies to first analyze the facial expressions of the individual by constantly monitoring an individual under observation. This monitoring is done with the help of OpenCV which captures the facial expression at an interval of 15 secs. Thousands of images per expression are used to train the model to aptly distinguish between expression using prominent Neural Network Methodologies of Forward and Backward Propagation. The identified expression is then be fed to a derivative system which plots a graph highlighting the changes in the expression. The graph acts as the crux of the proposed system. The project is important from the perspective of serving as an alternative to manual monitoring which are prone to errors and subjective in nature.

Circular Nodes in Neural Networks

1996 ◽  
Vol 8 (2) ◽  
pp. 390-402 ◽  
Author(s):  
Michael J. Kirby ◽  
Rick Miranda
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Dimensional Manifold ◽  
Almost Periodic ◽  
One Dimensional ◽  
Trefoil Knot ◽  
Hidden Layer ◽  
The Individual ◽  
Backward Propagation ◽  
Sivashinsky Equation

In the usual construction of a neural network, the individual nodes store and transmit real numbers that lie in an interval on the real line; the values are often envisioned as amplitudes. In this article we present a design for a circular node, which is capable of storing and transmitting angular information. We develop the forward and backward propagation formulas for a network containing circular nodes. We show how the use of circular nodes may facilitate the characterization and parameterization of periodic phenomena in general. We describe applications to constructing circular self-maps, periodic compression, and one-dimensional manifold decomposition. We show that a circular node may be used to construct a homeomorphism between a trefoil knot in ℝ3 and a unit circle. We give an application with a network that encodes the dynamic system on the limit cycle of the Kuramoto-Sivashinsky equation. This is achieved by incorporating a circular node in the bottleneck layer of a three-hidden-layer bottleneck network architecture. Exploiting circular nodes systematically offers a neural network alternative to Fourier series decomposition in approximating periodic or almost periodic functions.

Sign in / Sign up

Export Citation Format

Share Document