paper-with-me

홈 › Papers

Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation

2020-11-26 · Garvita Agarwal, Lauren Hay, Ia Iashvili, Benjamin Mannix, Christine McLean, Margaret Morris, Salvatore Rappoccio, Ulrich Schubert

A framework is presented to extract and understand decision-making information from a deep neural network (DNN) classifier of jet substructure tagging techniques. The general method studied is to provide expert variables that augment inputs ("eXpert AUGmented" variables, or XAUG variables), then apply layerwise relevance propagation (LRP) to networks both with and without XAUG variables. The XAUG variables are concatenated with the intermediate layers after network-specific operations (such as convolution or recurrence), and used in the final layers of the network. The results of comparing networks with and without the addition of XAUG variables show that XAUG variables can be used to interpret classifier behavior, increase discrimination ability when combined with low-level features, and in some cases capture the behavior of the classifier completely. The LRP technique can be used to find relevant information the network is using, and when combined with the XAUG variables, can be used to rank features, allowing one to find a reduced set of features that capture part of the network performance. In the studies presented, adding XAUG variables to low-level DNNs increased the efficiency of classifiers by as much as 30-40\%. In addition to performance improvements, an approach to quantify numerical uncertainties in the training of these DNNs is presented.

📄 PDF Abstract BibTeX arXiv:2011.13466

Code (1)

ubcms-xai/XAICoffea 공식 구현 tf

Tasks

Decision Making

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Towards Explainable Dialogue System: Explaining Intent Classification using Saliency Techniques

2021-12-01 · ICON 2021 12 · Ratnesh Joshi, Arindam Chatterjee, Asif Ekbal

Deep learning based methods have shown tremendous success in several Natural Language Processing (NLP) tasks. The recent trends in the usage of Deep Learning based models for natural language tasks have definitely produc…

intent-classificationIntent ClassificationIntent DetectionNatural Language Understanding

Explainability: Relevance based Dynamic Deep Learning Algorithm for Fault Detection and Diagnosis in Chemical Processes

2021-03-22 · Piyush Agarwal, Melih Tamer, Hector Budman

The focus of this work is on Statistical Process Control (SPC) of a manufacturing process based on available measurements. Two important applications of SPC in industrial settings are fault detection and diagnosis (FDD).…

Fault Detection

Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation

2020-02-24 · Mathilde Guillemot, Catherine Heusele, Rodolphe Korichi, Sylvianne Schnebert 외

The lack of transparency of neural networks stays a major break for their use. The Layerwise Relevance Propagation technique builds heat-maps representing the relevance of each input in the model s decision. The relevanc…

Generalization on the Enhancement of Layerwise Relevance Interpretability of Deep Neural Network

2020-09-05 · Erico Tjoa, Guan Cuntai

The practical application of deep neural networks are still limited by their lack of transparency. One of the efforts to provide explanation for decisions made by artificial intelligence (AI) is the use of saliency or he…

Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steering

2026-01-20 · Yuxin Chen, Zhengzhou Cai, Xiangtian Ji, Weixiang Zhao 외 arxiv

Mixture-of-Experts (MoE) architectures have shown strong multilingual capabilities, yet the internal mechanisms underlying performance gains and cross-language differences remain insufficiently understood. In this work, …