Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Practical Issues in Temporal Difference Learning
Machine Learning
A counterexample to temporal differences learning
Neural Computation
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Time Series Analysis: Forecasting and Control
Time Series Analysis: Forecasting and Control
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Realization of an Improved Adaptive Neuro-Fuzzy Inference System in DSP
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
A hybrid neural network and ARIMA model for water quality time series prediction
Engineering Applications of Artificial Intelligence
| Hi-index | 0.00 |
This paper investigates the use of the scaled conjugate gradient (SCG) algorithm in temporal-difference (TD) learning for time series prediction. Special emphasis is given on the implementation details, after examining the theoretical background of the algorithm and the learning methodology and how these could be combined. Simple time series (linear, sinusoidal, etc.) as well as more complex ones, coming from real data, are used to examine the behavior of this novel combination of learning algorithm and methodology. Preliminary experimental results indicate that the implementation as presented in this paper indeed works, but the performance (in terms of learning speed and generalization ability) of TD learning using the SCG algorithm is not as good as expected, at least on the representative problems examined. An attempt to rationalize these results is presented.