Neural network studies, 1. Comparison of overfitting and overtraining

By Igor V. Tetko, D. Livingstone, A. Luik. 1995

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Introduction to multi-layer feed-forward neural networks (1997, background): “The problem of overlitting and the importance of cross-validation were studied in [72].”
A review of the-state-of-the-art in data-driven approaches for building energy prediction (2020, methodology): “Through comparing the prediction accuracy between model training and model validation, overfitting or underfitting could be detected [99].”
When Neurons Fail - Technical Report (2016, background): “We do not require any additional learning (1)In machine learning, we only know a finite number of the values of the target function: the learning data set 2 Of course over-provisioning has its own cost: the need for larger learning data sets and a higher risk of over-fitting [42], two topics that ar”
A renaissance of neural networks in drug discovery (2016, methodology): “Overfitting can be avoided by the use of a validation set of compounds, also not used in training, that monitor the predictive performance of the neural network model and stop training when it starts to deteriorate [14,22].”
Global Optimization Algorithms -- Theory and Application (2009, background): “The phenomenon of overfitting is best known and can often be encountered in the field of artificial neural networks or in curve fitting(50) [131, 132, 133, 134, 135].”