What size net gives valid generalization?
Neural Computation
Practical neural network recipes in C++
Practical neural network recipes in C++
Initializing back propagation networks with prototypes
Neural Networks
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Beyond Moore's Law: The Interconnect Era
Computing in Science and Engineering
Physical Time-Series Prediction Using Second-Order Pipelined Recurrent Neural Network
ICAIS '02 Proceedings of the 2002 IEEE International Conference on Artificial Intelligence Systems (ICAIS'02)
Linear and nonlinear time series forecasting with artificial neural networks
Linear and nonlinear time series forecasting with artificial neural networks
Method of Analogs in Prediction of Short Time Series: An Expert-statistical Approach
Automation and Remote Control
Hi-index | 0.00 |
Short time series are characterized with no trend information, no randomness and lack of periodicity. That makes prediction based on them very difficult or even impossible. On the other side there is strong need for prediction based on limited amount of data in many areas of life and business. We here propose implementation of some architectures of artificial neural networks as a potential systematic solution of that problem as opposed to heuristics that are in use. Examples will be given related to verification of Moor's law that is respected for prediction in modern electronic production, and to prediction of quantities of obsolete computers.