Improving the Performance of Neural Networks in Regression Tasks Using Drawering
2017 International Joint Conference on Neural Networks (IJCNN)(2016)
摘要
The method presented extends a given regression neural network to make its performance improve. The modification affects the learning procedure only, hence the extension may be easily omitted during evaluation without any change in prediction. It means that the modified model may be evaluated as quickly as the original one but tends to perform better. This improvement is possible because the modification gives better expressive power, provides better behaved gradients and works as a regularization. The knowledge gained by the temporarily extended neural network is contained in the parameters shared with the original neural network. The only cost is an increase in learning time.
更多查看译文
关键词
neural network performance improvement,regression tasks,drawering,learning time
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络