Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Amina Adadi,Mohammed Berrada +1 more
Reads0
Chats0
TLDR
This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI, and review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.Abstract:
At the dawn of the fourth industrial revolution, we are witnessing a fast and widespread adoption of artificial intelligence (AI) in our daily life, which contributes to accelerating the shift towards a more algorithmic society. However, even with such unprecedented advancements, a key impediment to the use of AI-based systems is that they often lack transparency. Indeed, the black-box nature of these systems allows powerful predictions, but it cannot be directly explained. This issue has triggered a new debate on explainable AI (XAI). A research field holds substantial promise for improving trust and transparency of AI-based systems. It is recognized as the sine qua non for AI to continue making steady progress without disruption. This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI. Through the lens of the literature, we review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.read more
Citations
More filters
Journal ArticleDOI
MAPAS: a practical deep learning-based android malware detection system
TL;DR: In this article , the authors proposed MAPAS, a malware detection system that uses a lightweight classifier that calculates a similarity between API call graphs used for malicious activities and API call graph of applications that are going to be classified.
Proceedings ArticleDOI
Leveraging rationales to improve human task performance
Devleena Das,Sonia Chernova +1 more
TL;DR: In this article, the Rationale-Generating Algorithm (RGA) is proposed to generate rationales for utility-based computational methods, which are then used to explain what the system is doing.
Journal ArticleDOI
A Simple Convolutional Neural Network with Rule Extraction
TL;DR: This work presents a new rule extraction method applied to a typical CNN architecture used in Sentiment Analysis (SA), focusing on the textual data on which the CNN is trained with “tweets” of movie reviews.
Proceedings ArticleDOI
Passing the Data Baton : A Retrospective Analysis on Data Science Work and Workers
TL;DR: A retrospective analysis of data science work and workers as described within the data visualization, human computer interaction, and data science literature is conducted to synthesis a comprehensive model that describes dataScience work and breakdown to data scientists into nine distinct roles.
Proceedings ArticleDOI
Designing for Responsible Trust in AI Systems: A Communication Perspective
Q. Vera Liao,S. Shyam Sundar +1 more
TL;DR: A conceptual model called MATCH is developed, which describes how trustworthiness is communicated in AI systems through trustworthiness cues and how those cues are processed by people to make trust judgments, and proposes a checklist of requirements to help technology creators identify appropriate cues to use.
References
More filters
Proceedings Article
Distributed Representations of Words and Phrases and their Compositionality
TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
Posted Content
Distilling the Knowledge in a Neural Network
TL;DR: This work shows that it can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model and introduces a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse.
Book ChapterDOI
Visualizing and Understanding Convolutional Networks
Matthew D. Zeiler,Rob Fergus +1 more
TL;DR: A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.
Proceedings ArticleDOI
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
Journal ArticleDOI
Mastering the game of Go without human knowledge
David Silver,Julian Schrittwieser,Karen Simonyan,Ioannis Antonoglou,Aja Huang,Arthur Guez,Thomas Hubert,Lucas Baker,Matthew Lai,Adrian Bolton,Yutian Chen,Timothy P. Lillicrap,Fan Hui,Laurent Sifre,George van den Driessche,Thore Graepel,Demis Hassabis +16 more
TL;DR: An algorithm based solely on reinforcement learning is introduced, without human data, guidance or domain knowledge beyond game rules, that achieves superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.