paper-with-me

홈 › Papers

Demystifying Deep Neural Networks Through Interpretation: A Survey

2020-12-13 · Giang Dao, Minwoo Lee

Modern deep learning algorithms tend to optimize an objective metric, such as minimize a cross entropy loss on a training dataset, to be able to learn. The problem is that the single metric is an incomplete description of the real world tasks. The single metric cannot explain why the algorithm learn. When an erroneous happens, the lack of interpretability causes a hardness of understanding and fixing the error. Recently, there are works done to tackle the problem of interpretability to provide insights into neural networks behavior and thought process. The works are important to identify potential bias and to ensure algorithm fairness as well as expected performance.

📄 PDF Abstract BibTeX arXiv:2012.07119

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessSurvey

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Similar Papers 제목 키워드 기반

Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning

2023-08-08 · Abhilekha Dalal, Md Kamruzzaman Sarker, Adrita Barua, Eugene Vasserman 외

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would provide insights into the question of what a deep learning system has internally detected as …

Demystifying Neural Network Filter Pruning

2018-10-29 · NIPS Workshop CDNNRIA 2018 · Zhuwei Qin, Fuxun Yu, ChenChen Liu, Xiang Chen

Based on filter magnitude ranking (e.g. L1 norm), conventional filter pruning methods for Convolutional Neural Networks (CNNs) have been proved with great effectiveness in computation load reduction. Although effective, …

Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis

2018-02-26 · Tal Ben-Nun, Torsten Hoefler

Deep Neural Networks (DNNs) are becoming an important tool in modern computing applications. Accelerating their training is a major challenge and techniques range from distributed algorithms to low-level circuit design. …

Deep LearningNeural Architecture SearchStochastic Optimization

Demystifying Neural Style Transfer

2017-01-04 · Yanghao Li, Naiyan Wang, Jiaying Liu, Xiaodi Hou

Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry. Despite the amazing results, the principle of neural style transfer, especially why the Gram matrice…

Domain AdaptationStyle Transfer

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety

2025-06-05 · Seongmin Lee, Aeree Cho, Grace C. Kim, Shengyun Peng 외

As large language models (LLMs) see wider real-world use, understanding and mitigating their unsafe behaviors is critical. Interpretation techniques can reveal causes of unsafe outputs and guide safety, but such connecti…

NavigateSurvey