A study of the effect of noise injection on the training of artificial neural networks

We studied the effect of noise injection in overcoming the problem of overtraining in the training of artificial neural networks (ANNs) in comparison with other common approaches for overcoming this problem such as early stopping of the ANN training process and weight decay (which is similar to Bayesian artificial neural networks). We found from simulation studies and studies of a computer-aided diagnosis application that noise injection is effective in overcoming overtraining and is as effective as, or even more effective than, early stopping and weight decay.

[1]  Jocelyn Sietsma,et al.  Creating artificial neural networks that generalize , 1991, Neural Networks.

[2]  Guozhong An,et al.  The Effects of Adding Noise During Backpropagation Training on a Generalization Performance , 1996, Neural Computation.

[3]  T. Freer,et al.  Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. , 2001, Radiology.

[4]  M. Giger,et al.  Improving breast cancer diagnosis with computer-aided diagnosis. , 1999, Academic radiology.

[5]  Dan Cornford,et al.  Neural Network Modelling with Input Uncertainty: Theory and Application , 2000, J. VLSI Signal Process..

[6]  Petri Koistinen,et al.  Using additive noise in back-propagation training , 1992, IEEE Trans. Neural Networks.

[7]  K Doi,et al.  Improvement in radiologists' detection of clustered microcalcifications on mammograms. The potential of computer-aided diagnosis. , 1990, Investigative radiology.

[8]  R. F. Wagner,et al.  Assessment of medical imaging systems and computer aids: a tutorial review. , 2007, Academic radiology.

[9]  Murray H. Loew,et al.  Comparison of non-parametric methods for assessing classifier performance in terms of ROC parameters , 2004, 33rd Applied Imagery Pattern Recognition Workshop (AIPR'04).

[10]  Kiyotoshi Matsuoka,et al.  Noise injection into inputs in back-propagation learning , 1992, IEEE Trans. Syst. Man Cybern..

[11]  Berkman Sahiner,et al.  Classifier Performance Estimation Under the Constraint of a Finite Sample Size: Resampling Schemes Applied to Neural Network Classifiers , 2007, IJCNN.

[12]  C. D'Orsi,et al.  Influence of computer-aided detection on performance of screening mammography. , 2007, The New England journal of medicine.

[13]  C. Metz,et al.  "Proper" Binormal ROC Curves: Theory and Maximum-Likelihood Estimation. , 1999, Journal of mathematical psychology.

[14]  M. Giger,et al.  Breast US computer-aided diagnosis workstation: performance with a large clinical diagnostic population. , 2008, Radiology.

[15]  Y. Jiang,et al.  Comparison of two methods of adding jitter to artificial neural network training , 2004, CARS.

[16]  S. Astley,et al.  Single reading with computer-aided detection for screening mammography. , 2008, The New England journal of medicine.

[17]  J. Swets,et al.  Enhanced interpretation of diagnostic images. , 1988, Investigative radiology.

[18]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[19]  C. Metz,et al.  Maximum likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data. , 1998, Statistics in medicine.