Interpretability of Blackbox Machine Learning Models through Dataview Extraction and Shadow Model creation

02/02/2020
by   Rupam Patir, et al.
0

Deep learning models trained using massive amounts of data tend to capture one view of the data and its associated mapping. Different deep learning models built on the same training data may capture different views of the data based on the underlying techniques used. For explaining the decisions arrived by blackbox deep learning models, we argue that it is essential to reproduce that model's view of the training data faithfully. This faithful reproduction can then be used for explanation generation. We investigate two methods for data view extraction: hill-climbing approach and a GAN-driven approach. We then use this synthesized data for creating shadow models for explanation generation: Decision-Tree model and Formal Concept Analysis based model. We evaluate these approaches on a Blackbox model trained on public datasets and show its usefulness in explanation generation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/21/2021

Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital

When using machine learning techniques in decision-making processes, the...
research
05/22/2019

A framework for the extraction of Deep Neural Networks by leveraging public data

Machine learning models trained on confidential datasets are increasingl...
research
08/16/2023

Explainable Multi-View Deep Networks Methodology for Experimental Physics

Physical experiments often involve multiple imaging representations, suc...
research
11/04/2019

Explaining the Predictions of Any Image Classifier via Decision Trees

Despite outstanding contribution to the significant progress of Artifici...
research
09/06/2019

Mass Personalization of Deep Learning

We discuss training techniques, objectives and metrics toward mass perso...
research
06/22/2020

MaskIt: Masking for efficient utilization of incomplete public datasets for training deep learning models

A major challenge in training deep learning models is the lack of high q...
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...

Please sign up or login with your details

Forgot password? Click here to reset