• home
• current students
• graduate
• events

Presenter: Babak Keshavarz Hedayati
Supervisor:

Date: Fri, February 1, 2019
Time: 15:30:00 - 16:30:00
Place: EOW 430

ABSTRACT

ABSTRACT:
Neural networks are an important tool in creating complex data models. In this presentation, we explored the application of neural networks in data modeling and we presented methods that help improve generalization of the data models.
We proposed a set of heuristics that improved the generalization capability of the neural network models in regression and classification problems. To do so, we explored applying apprioi information in the form of regularization of the behavior of the models. We used smoothness and self-consistency as the
two regularized attributes that were enforced on the behavior of the neural networks in our model. We used our proposed heuristics to improve the performance neural network ensembles in regression problems (more specifically in quantitative structure-activity relationship (QSAR) modeling problems). We demonstrated that these heuristics result in significant improvements in the performance of the models we used. In addition, we developed an anomaly detection method to identify and exclude the outliers among unknown cases presented to the model. This is to ensure that the data model only makes a prediction on the outcome of the unknown cases that are within its domain of applicability. This filtering resulted in further improvement of the performance of the model in our experiments.
Furthermore, and through some modifications, we extended the application of our proposed heuristics to classification problems. We evaluated the performance of the
resulting classification models over several datasets and demonstrated that the regularizations we employed in our heuristics, had a positive effect on the performance of the data model across various classification problems as well.