Browsing School of Computer Science and Statistics by Author "Carney, John G."
Now showing items 1-4 of 4
-
Diversity versus Quality in Classification Ensembles based on Feature Selection
Cunningham, Padraig; Carney, John G. (Trinity College Dublin, Department of Computer Science, 2000-01)Feature subset-selection has emerged as a useful technique for creating diversity in ensembles ? particularly in classification ensembles. In this paper we argue that this diversity needs to be monitored in the creation ... -
The Epoch Interpretation of Learning
Carney, John G.; Cunningham, Padraig (Trinity College Dublin, Department of Computer Science, 1998-06)In this paper we propose a simple, alternative interpretation of backpropagation learning. We call this the ?epoch interpretation of learning? and show how it can be used to improve the performance of earlystopping based ... -
Neural network ensembles for financial time-series prediction and risk management
Carney, John G. (Trinity College (Dublin, Ireland). School of Computer Science & Statistics, 2000)Neural Network Ensembles for Financial Time-Series Prediction and Risk Management. Recently, neural networks have become popular tools for modelling financial markets. Much of this popularity can be attributed to the fact ... -
Stability Problems with Artificial Neural Networks and the Ensemble Solution
Cunningham, Padraig; Carney, John G.; Jacob, Saji (Trinity College Dublin, Department of Computer Science, 1999-10)Artificial Neural Networks (ANNs) are very popular as classification or regression mechanisms in medical decision support systems despite the fact that they are unstable predictors. This instability means that small ...