Influence-Directed Explanations for Deep Convolutional Networks

02/11/2018
by   Klas Leino, et al.
0

We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the net- work to identify neurons with high influence on the property and distribution of interest using an axiomatically justified influence measure, and then providing an interpretation for the concepts these neurons represent. We evaluate our approach by training convolutional neural net- works on MNIST, ImageNet, Pubfig, and Diabetic Retinopathy datasets. Our evaluation demonstrates that influence-directed explanations (1) identify influential concepts that generalize across instances, (2) help extract the essence of what the network learned about a class, (3) isolate individual features the network uses to make decisions and distinguish related instances, and (4) assist in understanding misclassifications.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 5

12/05/2018

Understanding Individual Decisions of CNNs via Contrastive Backpropagation

A number of backpropagation-based approaches such as DeConvNets, vanilla...
07/30/2017

Towards Visual Explanations for Convolutional Neural Networks via Input Resampling

The predictive power of neural networks often costs model interpretabili...
02/02/2018

Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations

Deep neural networks are complex and opaque. As they enter application i...
06/24/2020

Compositional Explanations of Neurons

We describe a procedure for explaining neurons in deep representations b...
06/22/2021

Towards Automated Evaluation of Explanations in Graph Neural Networks

Explaining Graph Neural Networks predictions to end users of AI applicat...
11/03/2020

MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks

Deep convolutional networks have been quite successful at various image ...
12/03/2014

Deeply learned face representations are sparse, selective, and robust

This paper designs a high-performance deep convolutional network (DeepID...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.