Improving Generalization Ability of Neural Networks Ensemble with Multi-Task Learning
نویسندگان
چکیده
Neural networks ensemble (NNE) is becoming an ad hoc topic in the machine learning community. However, redundant features will hurt the performance of NNE, so feature selection methods are developed to remove a part of the redundant features. Instead of only removing the features, multi-task learning can employ the removed redundant information to improve the prediction accuracy. The previous study used heuristic search methods to search the features for the input and/or the target, while in this paper, a novel algorithm, GA-MTL (genetic algorithm based multitask learning) is proposed to determine the features for the input and/or the target of NNE. Experimental results on the UCI data sets show that GA-MTL is easy to be used to improve the generalization performance of NNE and obtains better performance than the heuristic methods do.
منابع مشابه
Monitoring of Regional Low-Flow Frequency Using Artificial Neural Networks
Ecosystem of arid and semiarid regions of the world, much of the country lies in the sensitive and fragile environment Canvases are that factors in the extinction and destruction are easily destroyed in this paper, artificial neural networks (ANNs) are introduced to obtain improved regional low-flow estimates at ungauged sites. A multilayer perceptron (MLP) network is used to identify the funct...
متن کاملMachine learning algorithms in air quality modeling
Modern studies in the field of environment science and engineering show that deterministic models struggle to capture the relationship between the concentration of atmospheric pollutants and their emission sources. The recent advances in statistical modeling based on machine learning approaches have emerged as solution to tackle these issues. It is a fact that, input variable type largely affec...
متن کاملCombining Regression Estimators: GA-Based Selective Neural Network Ensemble
Neural network ensemble is a learning paradigm where a collection of neural networks is trained for the same task. In this paper, the relationship between the generalization ability of the neural network ensemble and the correlation of the individual neural networks constituting the ensemble is analyzed in the context of combining neural regression estimators, which reveals that ensembling a se...
متن کاملSoft Computing - Neural Networks Ensembles
Neural Network ensemble is a learning paradigm where a collection of finite number of neural networks is trained for the same task. It is understood that the generalization ability of neural networks, i.e., training many neural networks and then combining their predictions. ANN ensemble techniques have become very popular amongst neural network practitioners in a variety of ANN application doma...
متن کاملImproving Generalization Ability through Active Learning
In this paper, we discuss the problem of active training data selection for improving the generalization capability of a neural network. We look at the learning problem from a function approximation perspective and formalize it as an inverse problem. Based on this framework, we analytically derive a method of choosing a training data set optimized with respect to the Wiener optimization criteri...
متن کامل