New Neural Network Based on Ant Colony Algorithm for Financial Data Forecasting

2008 ◽  
Author(s):  
W. Gao
Keyword(s):  
Neural Network ◽  
Ant Colony Algorithm ◽  
Financial Data ◽  
Ant Colony

Application of Ant Colony Algorithms and Neural Networks in Fault Diagnosis

2014 ◽  
Vol 556-562 ◽  
pp. 3014-3017
Author(s):  
Jing Bo Yu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Ant Colony Algorithm ◽  
Ant Colony ◽  
Ant Colony Algorithms ◽  
Weak Points ◽  
Diagnosis Method ◽  
Computational Simplicity ◽  
Minimum Points ◽  
Neural Network Technology

Neural network technology is widely applied due to its computational simplicity and versatility. But, this method has some weak points, for example, slow convergence, less accurate and easy to fall into local minimum points. Combined ant colony algorithm and neural network for fault diagnosis, it can overcome the limitations of a single fault diagnosis method. Ant colony neural network method is applied to gearbox fault diagnosis, the results show that the diagnosis with characteristics of high precision, strong scientific and practical wider.

Ant Colony Algorithm Based on Improved Neural Network Algorithm and its Application

2014 ◽  
Vol 543-547 ◽  
pp. 2116-2119
Author(s):  
Qing Qing Zhang ◽  
Qian Zhang ◽  
Yue Jiang Feng
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Ant Colony Algorithm ◽  
Bp Algorithm ◽  
Ant Colony ◽  
Ant Colony System ◽  
Bp Network ◽  
Actual Problem ◽  
Node Number ◽  
Network Learning

This paper mainly to the ant colony algorithm ant colony system (application pseudo-random proportional rules) and add adaptive learning, momentum BP algorithm of these three together was improved, established a hybrid algorithm, to a certain extent overcome the BP algorithm is easy to fall into local minimum value, slow convergence speed, and achieved satisfactory results. Generally speaking, the performance of BP network is composed of two components: the topology of the network and network learning algorithm. The topology of the network design especially hidden node number should be how to choose the number of neurons more reasonable there is no unified theory, the solution actual problem at present is more of the experience and the method of combining the test to determine the optimal number of hidden nodes. This paper mainly discussed the structure of neural network to determine later, network learning process problems.

Sign in / Sign up

Export Citation Format

Share Document