Explanatory Masks for Neural Network Interpretability

11/15/2019
by   Lawrence Phillips, et al.
0

Neural network interpretability is a vital component for applications across a wide variety of domains. In such cases it is often useful to analyze a network which has already been trained for its specific purpose. In this work, we develop a method to produce explanation masks for pre-trained networks. The mask localizes the most important aspects of each input for prediction of the original network. Masks are created by a secondary network whose goal is to create as small an explanation as possible while still preserving the predictive accuracy of the original network. We demonstrate the applicability of our method for image classification with CNNs, sentiment analysis with RNNs, and chemical property prediction with mixed CNN/RNN architectures.

READ FULL TEXT
research
10/15/2022

DProtoNet: Decoupling the inference module and the explanation module enables neural networks to have better accuracy and interpretability

The interpretation of decisions made by neural networks is the focus of ...
research
03/03/2020

Fully Convolutional Networks for Automatically Generating Image Masks to Train Mask R-CNN

This paper proposes a novel automatically generating image masks method ...
research
12/07/2017

ChemNet: A Transferable and Generalizable Deep Neural Network for Small-Molecule Property Prediction

With access to large datasets, deep neural networks (DNN) have achieved ...
research
10/23/2019

Using Segmentation Masks in the ICCV 2019 Learning to Drive Challenge

In this work we predict vehicle speed and steering angle given camera im...
research
09/25/2019

Multi-Dimensional Explanation of Reviews

Neural models achieved considerable improvement for many natural languag...
research
01/19/2018

Piggyback: Adding Multiple Tasks to a Single, Fixed Network by Learning to Mask

This work presents a method for adding multiple tasks to a single, fixed...
research
10/05/2022

How Erdös and Rényi Win the Lottery

Random masks define surprisingly effective sparse neural network models,...

Please sign up or login with your details

Forgot password? Click here to reset