Role of influence functions in model interpretability (Conference Presentation)

Supriyo Chakraborty; Jorge Ortiz; Simon Julier

doi:10.1117/12.2306009

14 May 2018 Role of influence functions in model interpretability (Conference Presentation)

Supriyo Chakraborty, Jorge Ortiz, Simon Julier

Proceedings Volume 10635, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR IX; 1063505 (2018) https://doi.org/10.1117/12.2306009
Event: SPIE Defense + Security, 2018, Orlando, FL, United States

Abstract

Deep Neural Networks (DNNs) have achieved near human and in some cases super human accuracies in tasks such as machine translation, image classification, speech processing and so on. However, despite their enormous success these models are often used as black-boxes with very little visibility into their working. This opacity of the models often presents hindrance towards the adoption of these models for mission-critical and human-machine hybrid networks. In this paper, we will explore the role of influence functions towards opening up these black-box models and for providing interpretability of their output. Influence functions are used to characterize the impact of training data on the model parameters. We will use these functions to analytically understand how the parameters are adjusted during the model training phase to embed the information contained in the training dataset. In other words, influence functions allows us to capture the change in the model parameters due to the training data. We will then use these parameters to provide interpretability of the model output for test data points.

Conference Presentation

Citation Download Citation

Supriyo Chakraborty, Jorge Ortiz, and Simon Julier "Role of influence functions in model interpretability (Conference Presentation)", Proc. SPIE 10635, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR IX, 1063505 (14 May 2018); https://doi.org/10.1117/12.2306009

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available