Now You See Me (CME): Concept-based Model Extraction

by   Dmitry Kazhdan, et al.

Deep Neural Networks (DNNs) have achieved remarkable performance on a range of tasks. A key step to further empowering DNN-based approaches is improving their explainability. In this work we present CME: a concept-based model extraction framework, used for analysing DNN models via concept-based extracted models. Using two case studies (dSprites, and Caltech UCSD Birds), we demonstrate how CME can be used to (i) analyse the concept information learned by a DNN model (ii) analyse how a DNN uses this concept information when predicting output labels (iii) identify key concept information that can further improve DNN predictive performance (for one of the case studies, we showed how model accuracy can be improved by over 14 available concepts).


MEME: Generating RNN Model Explanations via Model Extraction

Recurrent Neural Networks (RNNs) have achieved remarkable performance on...

Concept-Monitor: Understanding DNN training through individual neurons

In this work, we propose a general framework called Concept-Monitor to h...

Enhancing Deep Learning with Scenario-Based Override Rules: a Case Study

Deep neural networks (DNNs) have become a crucial instrument in the soft...

A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation

In recent years, concept-based approaches have emerged as some of the mo...

Cognitive Explainers of Graph Neural Networks Based on Medical Concepts

Although deep neural networks (DNN) have achieved state-of-the-art perfo...

Detecting Deep Neural Network Defects with Data Flow Analysis

Deep neural networks (DNNs) are shown to be promising solutions in many ...

Please sign up or login with your details

Forgot password? Click here to reset