Investigating Decision Boundaries of Trained Neural Networks

08/07/2019
by   Roozbeh Yousefzadeh, et al.
0

Deep learning models have been the subject of study from various perspectives, for example, their training process, interpretation, generalization error, robustness to adversarial attacks, etc. A trained model is defined by its decision boundaries, and therefore, many of the studies about deep learning models speculate about the decision boundaries, and sometimes make simplifying assumptions about them. So far, finding exact points on the decision boundaries of trained deep models has been considered an intractable problem. Here, we compute exact points on the decision boundaries of these models and provide mathematical tools to investigate the surfaces that define the decision boundaries. Through numerical results, we confirm that some of the speculations about the decision boundaries are accurate, some of the computational methods can be improved, and some of the simplifying assumptions may be unreliable, for models with nonlinear activation functions. We advocate for verification of simplifying assumptions and approximation methods, wherever they are used. Finally, we demonstrate that the computational practices used for finding adversarial examples can be improved and computing the closest point on the decision boundary reveals the weakest vulnerability of a model against adversarial attack.

READ FULL TEXT
research
01/03/2020

Auditing and Debugging Deep Learning Models via Decision Boundaries: Individual-level and Group-level Analysis

Deep learning models have been criticized for their lack of easy interpr...
research
01/15/2021

Heating up decision boundaries: isocapacitory saturation, adversarial scenarios and generalization bounds

In the present work we study classifiers' decision boundaries via Browni...
research
12/18/2020

ROBY: Evaluating the Robustness of a Deep Model by its Decision Boundaries

With the successful application of deep learning models in many real-wor...
research
02/15/2020

Hold me tight! Influence of discriminative features on deep network boundaries

Important insights towards the explainability of neural networks and the...
research
11/25/2022

The Vanishing Decision Boundary Complexity and the Strong First Component

We show that unlike machine learning classifiers, there are no complex b...
research
02/07/2022

Redactor: Targeted Disinformation Generation using Probabilistic Decision Boundaries

Information leakage is becoming a critical problem as various informatio...
research
03/07/2020

Geometry and Topology of Deep Neural Networks' Decision Boundaries

Geometry and topology of decision regions are closely related with class...

Please sign up or login with your details

Forgot password? Click here to reset