Finding and removing Clever Hans: Using explanation methods to debug and improve deep models
Wojciech Samek,Christopher J. Anders,Leander Weber,Leander Weber,Ray Jones,Reade A. Quinton,David Neumann,Wojciech Samek,Klaus-Robert Müller,Sebastian Lapuschkin +9 more
Reads0
Chats0
TLDR
In this article, a scalable quantification of artifactual and poisoned classes where the machine learning models under study exhibit Clever Hans behavior is proposed, and several approaches are collectively termed as Class Artifact Compensation, which are able to effectively reduce a model's Clever Hans behaviour.About:
This article is published in Information Fusion.The article was published on 2022-01-01 and is currently open access. It has received 23 citations till now. The article focuses on the topics: Computer science & Spurious relationship.read more
Citations
More filters
Book ChapterDOI
Explainable AI Methods - A Brief Overview
TL;DR: In this article , explainable artificial intelligence (xAI) is an established field with a vibrant community that has developed a variety of very successful approaches to explain and interpret predictions of complex machine learning models such as deep neural networks.
Journal ArticleDOI
Explain and improve: LRP-inference fine-tuning for image captioning models
Jiamei Sun,Wojciech Samek,Sebastian Lapuschkin,Wojciech Samek,Alexander Binder,Alexander Binder +5 more
TL;DR: An LRP-inference fine-tuning strategy is designed that reduces the issue of object hallucination in image captioning models, and meanwhile, maintains the sentence fluency.
Journal ArticleDOI
Towards robust explanations for deep neural networks
TL;DR: In this paper, a unified theoretical framework for deriving bounds on the maximal manipulability of a model is developed. And three different techniques to boost robustness against manipulation are presented: weight decay, smoothing activation functions, and minimizing the Hessian of the network.
Journal ArticleDOI
2020 International brain–computer interface competition: A review
Ji-Hoon Jeong,Jeong-Hyun Cho,Young Eun Lee,Seo-Hyun Lee,Gi Hwan Shin,Young-Seok Kweon,José del R. Millán,Klaus-Robert Müller,Seong-Whan Lee +8 more
TL;DR: Remarkable BCI advances were identified through the 2020 competition and indicated some trends of interest to BCI researchers.
Journal ArticleDOI
Toward Explainable Artificial Intelligence for Regression Models: A methodological perspective
TL;DR: XAIR as discussed by the authors provides theoretical insights and analysis for explainable AI for regression and classification tasks, and provides demonstrations of XAIR on genuine practical regression problems, and finally discuss the challenges remaining for the field.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Journal ArticleDOI
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.