NeuCEPT: Locally Discover Neural Networks' Mechanism via Critical Neurons Identification with Precision Guarantee

09/18/2022
by   Minh N. Vu, et al.
0

Despite recent studies on understanding deep neural networks (DNNs), there exists numerous questions on how DNNs generate their predictions. Especially, given similar predictions on different input samples, are the underlying mechanisms generating those predictions the same? In this work, we propose NeuCEPT, a method to locally discover critical neurons that play a major role in the model's predictions and identify model's mechanisms in generating those predictions. We first formulate a critical neurons identification problem as maximizing a sequence of mutual-information objectives and provide a theoretical framework to efficiently solve for critical neurons while keeping the precision under control. NeuCEPT next heuristically learns different model's mechanisms in an unsupervised manner. Our experimental results show that neurons identified by NeuCEPT not only have strong influence on the model's predictions but also hold meaningful information about model's mechanisms.

READ FULL TEXT

page 2

page 5

page 9

research
12/24/2021

CatchBackdoor: Backdoor Testing by Critical Trojan Neural Path Identification via Differential Fuzzing

The success of deep neural networks (DNNs) in real-world applications ha...
research
10/10/2020

Training Binary Neural Networks through Learning with Noisy Supervision

This paper formalizes the binarization operations over neural networks f...
research
07/30/2017

Towards Visual Explanations for Convolutional Neural Networks via Input Resampling

The predictive power of neural networks often costs model interpretabili...
research
02/26/2019

Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification

Deep neural networks (DNNs) have been shown lack of robustness for the v...
research
05/05/2023

Repairing Deep Neural Networks Based on Behavior Imitation

The increasing use of deep neural networks (DNNs) in safety-critical sys...
research
06/16/2023

Enhancing Fault Resilience of QNNs by Selective Neuron Splitting

The superior performance of Deep Neural Networks (DNNs) has led to their...

Please sign up or login with your details

Forgot password? Click here to reset