paper-with-me

홈 › Papers

Learning how to explain neural networks: PatternNet and PatternAttribution

2017-05-16 · ICLR 2018 1 · Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber, Klaus-Robert Müller, Dumitru Erhan, Been Kim, Sven Dähne

DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a linear model. Yet they are used on multi-layer networks with millions of parameters. This is a cause for concern since linear models are simple neural networks. We argue that explanation methods for neural nets should work reliably in the limit of simplicity, the linear models. Based on our analysis of linear models we propose a generalization that yields two explanation techniques (PatternNet and PatternAttribution) that are theoretically sound for linear models and produce improved explanations for deep networks.

📄 PDF Abstract BibTeX arXiv:1705.05598

Code (4)

DFKI-NLP/language-attributions pytorch
adrhill/explainableai.jl pytorch
dianna-ai/dianna tf
pikinder/nn-patterns

Similar Papers 제목 키워드 기반

Scrutinizing XAI using linear ground-truth data with suppressor variables

2021-11-14 · Rick Wilming, Céline Budding, Klaus-Robert Müller, Stefan Haufe

Machine learning (ML) is increasingly often used to inform high-stakes decisions. As complex ML models (e.g., deep neural networks) are often considered black boxes, a wealth of procedures has been developed to shed ligh…

Explainable Artificial Intelligence (XAI)Feature Importance

iNNvestigate neural networks!

2018-08-13 · Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer, Miriam Hägele 외

In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. Therefore, it is crucial that domain specia…

Interpretable Machine Learning

Learning Explanations from Language Data

2018-08-13 · WS 2018 11 · David Harbecke, Robert Schwarzenberg, Christoph Alt

PatternAttribution is a recent method, introduced in the vision domain, that explains classifications of deep neural networks. We demonstrate that it also generates meaningful interpretations in the language domain.

Pattern-Guided Integrated Gradients

2020-07-21 · Robert Schwarzenberg, Steffen Castle

Integrated Gradients (IG) and PatternAttribution (PA) are two established explainability methods for neural networks. Both methods are theoretically well-founded. However, they were designed to overcome different challen…

PatternNet: Visual Pattern Mining with Deep Neural Network

2017-03-18 · Hongzhi Li, Joseph G. Ellis, Lei Zhang, Shih-Fu Chang

Visual patterns represent the discernible regularity in the visual world. They capture the essential nature of visual objects or scenes. Understanding and modeling visual patterns is a fundamental problem in visual recog…

image-classificationImage Classification