VECA: A Method for Detecting Overfitting in Neural Networks (Student Abstract)


  • Liangzhu Ge Tianjin University
  • Yuexian Hou Tianjin University
  • Yaju Jiang Tianjin University
  • Shuai Yao Tianjin University
  • Chao Yang Alibaba Group



Despite their widespread applications, deep neural networks often tend to overfit the training data. Here, we propose a measure called VECA (Variance of Eigenvalues of Covariance matrix of Activation matrix) and demonstrate that VECA is a good predictor of networks' generalization performance during the training process. Experiments performed on fully-connected networks and convolutional neural networks trained on benchmark image datasets show a strong correlation between test loss and VECA, which suggest that we can calculate the VECA to estimate generalization performance without sacrificing training data to be used as a validation set.




How to Cite

Ge, L., Hou, Y., Jiang, Y., Yao, S., & Yang, C. (2020). VECA: A Method for Detecting Overfitting in Neural Networks (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13791-13792.



Student Abstract Track