Evolutionary learning algorithm for projection neural networks

1997 ◽  
pp. 136-145
Author(s):  
Min Woong Hwang ◽  
Jin Young Choi
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Evolutionary Learning

Study of the operation of an artificial neural network that works in the electric network in order to prevent emergency conditions.

2020 ◽  
Vol 14 (1) ◽  
pp. 48-54
Author(s):  
D. Ostrenko ◽  
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Electricity Consumption ◽  
Electrical Energy ◽  
Energy System ◽  
Electrical Networks ◽  
Electric Networks ◽  
Electric Network ◽  
Time Dynamics ◽  
Emergency Situations

Emergency modes in electrical networks, arising for various reasons, lead to a break in the transmission of electrical energy on the way from the generating facility to the consumer. In most cases, such time breaks are unacceptable (the degree depends on the class of the consumer). Therefore, an effective solution is to both deal with the consequences, use emergency input of the reserve, and prevent these emergency situations by predicting events in the electric network. After analyzing the source [1], it was concluded that there are several methods for performing the forecast of emergency situations in electric networks. It can be: technical analysis, operational data processing (or online analytical processing), nonlinear regression methods. However, it is neural networks that have received the greatest application for solving these tasks. In this paper, we analyze existing neural networks used to predict processes in electrical systems, analyze the learning algorithm, and propose a new method for using neural networks to predict in electrical networks. Prognostication in electrical engineering plays a key role in shaping the balance of electricity in the grid, influencing the choice of mode parameters and estimated electrical loads. The balance of generation of electricity is the basis of technological stability of the energy system, its violation affects the quality of electricity (there are frequency and voltage jumps in the network), which reduces the efficiency of the equipment. Also, the correct forecast allows to ensure the optimal load distribution between the objects of the grid. According to the experience of [2], different methods are usually used for forecasting electricity consumption and building customer profiles, usually based on the analysis of the time dynamics of electricity consumption and its factors, the identification of statistical relationships between features and the construction of models.

FUNCOM: A constrained learning algorithm for fuzzy neural networks

2000 ◽  
Vol 112 (1) ◽  
pp. 1-26 ◽  
Author(s):  
Paris Mastorocostas ◽  
John Theocharis
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Fuzzy Neural Networks ◽  
Fuzzy Neural ◽  
Constrained Learning

Sliding mode incremental learning algorithm for interval type-2 Takagi–Sugeno–Kang fuzzy neural networks

2012 ◽  
Vol 3 (3) ◽  
pp. 179-188 ◽  
Author(s):  
Sevil Ahmed ◽  
Nikola Shakev ◽  
Andon Topalov ◽  
Kostadin Shiev ◽  
Okyay Kaynak
Keyword(s):  
Neural Networks ◽  
Incremental Learning ◽  
Sliding Mode ◽  
Learning Algorithm ◽  
Fuzzy Neural Networks ◽  
Fuzzy Neural ◽  
Interval Type ◽  
Takagi Sugeno

Effective Transfer Learning Algorithm in Spiking Neural Networks

2021 ◽  
pp. 1-13
Author(s):  
Qiugang Zhan ◽  
Guisong Liu ◽  
Xiurui Xie ◽  
Guolin Sun ◽  
Huajin Tang
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Learning Algorithm ◽  
Spiking Neural Networks ◽  
Effective Transfer

Improving the Generalization Properties of Radial Basis Function Neural Networks

1991 ◽  
Vol 3 (4) ◽  
pp. 579-588 ◽  
Author(s):  
Chris Bishop
Keyword(s):  
Neural Networks ◽  
Radial Basis Function ◽  
Basis Function ◽  
Learning Algorithm ◽  
Error Functional ◽  
Radial Basis ◽  
The Error Functional ◽  
Network Mapping ◽  
Nonlinear Mappings

An important feature of radial basis function neural networks is the existence of a fast, linear learning algorithm in a network capable of representing complex nonlinear mappings. Satisfactory generalization in these networks requires that the network mapping be sufficiently smooth. We show that a modification to the error functional allows smoothing to be introduced explicitly without significantly affecting the speed of training. A simple example is used to demonstrate the resulting improvement in the generalization properties of the network.

Sign in / Sign up

Export Citation Format

Share Document