Artificial neural networks with evolutionary instance selection for financial forecasting

2006 ◽  
Vol 30 (3) ◽  
pp. 519-526 ◽  
Author(s):  
Kyoung-jae Kim
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Instance Selection ◽  
Financial Forecasting ◽  
Selection For ◽  
Artificial Neural

ANALYSIS OF DOCUMENTS RANKING ALGORITHMS BASED ON THE ARTIFICIAL NEURAL NETWORKS

2019 ◽  
Author(s):  
Andrew Lishchytovych ◽  
Volodymyr Pavlenko
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Network Architecture ◽  
Search Algorithm ◽  
Network Algorithms ◽  
Text Document ◽  
Ranking Algorithms ◽  
Selection For ◽  
Artificial Neural

The object of this study is to analyse the effectiveness of document ran­ king algorithms in search engines that use artificial neural networks to match the texts. The purpose of the study was to inspect a neural network model of text document ran­ king that uses clustering, factor analysis, and multi-layered network architecture. The work of neural network algorithms was compared with the standard statistical search algorithm OkapiBM25. The result of the study is to evaluate the effectiveness of the use of particular models and to recommend model selection for specific datasets.

Selection for Wandering Behavior in a Small Robot

1994 ◽  
Vol 2 (1) ◽  
pp. 101-116 ◽  
Author(s):  
Orazio Miglino ◽  
Kourosh Nafasi ◽  
Charles E. Taylor
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Computational Complexity ◽  
Random Noise ◽  
Effective Means ◽  
Selection For ◽  
Artificial Neural ◽  
Small Robot ◽  
Fixed Period

We have evolved artificial neural networks to control the wandering behavior of small robots. The task and environment were very simple—to touch as many squares in a grid as possible during a fixed period of time. A number of the simulated robots were embodied in a small Lego™ robot, controlled by a Motorola™ 6811 processor; and their performance was compared to the simulations. We observed that: (a) evolution was an effective means to program the robot's behavior; (b) progress was characterized by sharply stepped periods of improvement, separated by periods of stasis that corresponded to levels of behavioral/computational complexity; and (c) the simulated and realized robots behaved quite similarly, the realized robots in some cases outperforming the simulated ones. Introducing random noise to the simulations improved the fit somewhat (from r = 0.73 to 0.79). Hybrid simulated/embodied selection regimes for evolutionary robots are discussed.

Sign in / Sign up

Export Citation Format

Share Document