New Perspective of Interpretability of Deep Neural Networks

09/12/2019
by   Masanari Kimura, et al.
0

Deep neural networks (DNNs) are known as black-box models. In other words, it is difficult to interpret the internal state of the model. Improving the interpretability of DNNs is one of the hot research topics. However, at present, the definition of interpretability for DNNs is vague, and the question of what is a highly explanatory model is still controversial. To address this issue, we provide the definition of the human predictability of the model, as a part of the interpretability of the DNNs. The human predictability proposed in this paper is defined by easiness to predict the change of the inference when perturbating the model of the DNNs. In addition, we introduce one example of high human-predictable DNNs. We discuss that our definition will help to the research of the interpretability of the DNNs considering various types of applications.

READ FULL TEXT

page 5

page 6

research
03/12/2017

Improving Interpretability of Deep Neural Networks with Semantic Information

Interpretability of deep neural networks (DNNs) is essential since it en...
research
03/30/2020

Architecture Disentanglement for Deep Neural Networks

Deep Neural Networks (DNNs) are central to deep learning, and understand...
research
05/26/2023

Laplace-Approximated Neural Additive Models: Improving Interpretability with Bayesian Inference

Deep neural networks (DNNs) have found successful applications in many f...
research
07/27/2022

Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks

The last decade of machine learning has seen drastic increases in scale ...
research
01/22/2021

i-Algebra: Towards Interactive Interpretability of Deep Neural Networks

Providing explanations for deep neural networks (DNNs) is essential for ...
research
10/22/2020

Towards falsifiable interpretability research

Methods for understanding the decisions of and mechanisms underlying dee...
research
12/01/2022

Experimental Observations of the Topology of Convolutional Neural Network Activations

Topological data analysis (TDA) is a branch of computational mathematics...

Please sign up or login with your details

Forgot password? Click here to reset