LGMLJun 24, 2017

Methods for Interpreting and Understanding Deep Neural Networks

arXiv:1706.07979v12515 citations
Originality Synthesis-oriented
AI Analysis

It provides an introductory tutorial for researchers and practitioners in machine learning, but is incremental as it summarizes existing methods.

The paper addresses the problem of interpreting deep neural network models and explaining their predictions by introducing recently proposed techniques, theory, and practical recommendations for efficient use on real data, with discussions of applications.

This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. It introduces some recently proposed techniques of interpretation, along with theory, tricks and recommendations, to make most efficient use of these techniques on real data. It also discusses a number of practical applications.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes