Applied AI letters最新文献_第5页

Issue Information 问题信息

Applied AI letters Pub Date : 2022-02-01 DOI: 10.1002/ail2.25

引用次数: 0

Qualitative Investigation in Explainable Artificial Intelligence: Further Insight from Social Science 可解释人工智能的定性研究——来自社会科学的进一步认识

Applied AI letters Pub Date : 2022-01-17 DOI: 10.1002/ail2.64

Adam J. Johs, Denise E. Agosto, Rosina O. Weber

引用次数: 2

Generative model-enhanced human motion prediction 生成模型增强的人体运动预测

Applied AI letters Pub Date : 2022-01-17 DOI: 10.1002/ail2.63

Anthony Bourached, Ryan-Rhys Griffiths, Robert Gray, Ashwani Jha, Parashkev Nachev

引用次数: 12

Deep Learning does not Replace Bayesian Modeling: Comparing research use via citation counting 深度学习不能取代贝叶斯建模：通过引文计数比较研究用途

Applied AI letters Pub Date : 2022-01-05 DOI: 10.1002/ail2.62

B. Baldwin

引用次数: 0

DARPA's explainable AI (XAI) program: A retrospective DARPA的可解释人工智能(XAI)计划:回顾

Applied AI letters Pub Date : 2021-12-04 DOI: 10.1002/ail2.61

David Gunning, Eric Vorm, Jennifer Yunyan Wang, Matt Turek

引用次数: 23

Reframing explanation as an interactive medium: The EQUAS (Explainable QUestion Answering System) project 将解释作为一种互动媒介:EQUAS(可解释问答系统)项目

Applied AI letters Pub Date : 2021-11-30 DOI: 10.1002/ail2.60

William Ferguson, Dhruv Batra, Raymond Mooney, Devi Parikh, Antonio Torralba, David Bau, David Diller, Josh Fasching, Jaden Fiotto-Kaufman, Yash Goyal, Jeff Miller, Kerry Moffitt, Alex Montes de Oca, Ramprasaath R. Selvaraju, Ayush Shrivastava, Jialin Wu, Stefan Lee

{"title":"Reframing explanation as an interactive medium: The EQUAS (Explainable QUestion Answering System) project","authors":"William Ferguson, Dhruv Batra, Raymond Mooney, Devi Parikh, Antonio Torralba, David Bau, David Diller, Josh Fasching, Jaden Fiotto-Kaufman, Yash Goyal, Jeff Miller, Kerry Moffitt, Alex Montes de Oca, Ramprasaath R. Selvaraju, Ayush Shrivastava, Jialin Wu, Stefan Lee","doi":"10.1002/ail2.60","DOIUrl":"10.1002/ail2.60","url":null,"abstract":"This letter is a retrospective analysis of our team's research for the Defense Advanced Research Projects Agency Explainable Artificial Intelligence project. Our initial approach was to use salience maps, English sentences, and lists of feature names to explain the behavior of deep-learning-based discriminative systems, with particular focus on visual question answering systems. We found that presenting static explanations along with answers led to limited positive effects. By exploring various combinations of machine and human explanation production and consumption, we evolved a notion of explanation as an interactive process that takes place usually between humans and artificial intelligence systems but sometimes within the software system. We realized that by interacting via explanations people could task and adapt machine learning (ML) agents. We added affordances for editing explanations and modified the ML system to act in accordance with the edits to produce an interpretable interface to the agent. Through this interface, editing an explanation can adapt a system's performance to new, modified purposes. This deep tasking, wherein the agent knows its objective and the explanation for that objective, will be critical to enable higher levels of autonomy.","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"2 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.60","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41941827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards structured NLP interpretation via graph explainers 通过图形解释器实现结构化的NLP解释

Applied AI letters Pub Date : 2021-11-26 DOI: 10.1002/ail2.58

Hao Yuan, Fan Yang, Mengnan Du, Shuiwang Ji, Xia Hu

{"title":"Towards structured NLP interpretation via graph explainers","authors":"Hao Yuan, Fan Yang, Mengnan Du, Shuiwang Ji, Xia Hu","doi":"10.1002/ail2.58","DOIUrl":"10.1002/ail2.58","url":null,"abstract":"Natural language processing (NLP) models have been increasingly deployed in real-world applications, and interpretation for textual data has also attracted dramatic attention recently. Most existing methods generate feature importance interpretation, which indicate the contribution of each word towards a specific model prediction. Text data typically possess highly structured characteristics and feature importance explanation cannot fully reveal the rich information contained in text. To bridge this gap, we propose to generate structured interpretations for textual data. Specifically, we pre-process the original text using dependency parsing, which could transform the text from sequences into graphs. Then graph neural networks (GNNs) are utilized to classify the transformed graphs. In particular, we explore two kinds of structured interpretation for pre-trained GNNs: edge-level interpretation and subgraph-level interpretation. Experimental results over three text datasets demonstrate that the structured interpretation can better reveal the structured knowledge encoded in the text. The experimental analysis further indicates that the proposed interpretations can faithfully reflect the decision-making process of the GNN model.","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"2 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.58","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43677736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Explainable activity recognition in videos: Lessons learned 视频中可解释的活动识别:经验教训

Applied AI letters Pub Date : 2021-11-26 DOI: 10.1002/ail2.59

Chiradeep Roy, Mahsan Nourani, Donald R. Honeycutt, Jeremy E. Block, Tahrima Rahman, Eric D. Ragan, Nicholas Ruozzi, Vibhav Gogate

{"title":"Explainable activity recognition in videos: Lessons learned","authors":"Chiradeep Roy, Mahsan Nourani, Donald R. Honeycutt, Jeremy E. Block, Tahrima Rahman, Eric D. Ragan, Nicholas Ruozzi, Vibhav Gogate","doi":"10.1002/ail2.59","DOIUrl":"10.1002/ail2.59","url":null,"abstract":"We consider the following activity recognition task: given a video, infer the set of activities being performed in the video and assign each frame to an activity. This task can be solved using modern deep learning architectures based on neural networks or conventional classifiers such as linear models and decision trees. While neural networks exhibit superior predictive performance as compared with decision trees and linear models, they are also uninterpretable and less explainable. We address this accuracy-explanability gap using a novel framework that feeds the output of a deep neural network to an interpretable, tractable probabilistic model called dynamic cutset networks, and performs joint reasoning over the two to answer questions. The neural network helps achieve high accuracy while dynamic cutset networks because of their polytime probabilistic reasoning capabilities make the system more explainable. We demonstrate the efficacy of our approach by using it to build three prototype systems that solve human-machine tasks having varying levels of difficulty using cooking videos as an accessible domain. We describe high-level technical details and key lessons learned in our human subjects evaluations of these systems.","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"2 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.59","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43572819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Toward explainable and advisable model for self-driving cars 为自动驾驶汽车建立一个可解释且可行的模型

Applied AI letters Pub Date : 2021-11-23 DOI: 10.1002/ail2.56

Jinkyu Kim, Anna Rohrbach, Zeynep Akata, Suhong Moon, Teruhisa Misu, Yi-Ting Chen, Trevor Darrell, John Canny

{"title":"Toward explainable and advisable model for self-driving cars","authors":"Jinkyu Kim, Anna Rohrbach, Zeynep Akata, Suhong Moon, Teruhisa Misu, Yi-Ting Chen, Trevor Darrell, John Canny","doi":"10.1002/ail2.56","DOIUrl":"10.1002/ail2.56","url":null,"abstract":"Humans learn to drive through both practice and theory, for example, by studying the rules, while most self-driving systems are limited to the former. Being able to incorporate human knowledge of typical causal driving behavior should benefit autonomous systems. We propose a new approach that learns vehicle control with the help of human advice. Specifically, our system learns to summarize its visual observations in natural language, predict an appropriate action response (eg, “I see a pedestrian crossing, so I stop”), and predict the controls, accordingly. Moreover, to enhance the interpretability of our system, we introduce a fine-grained attention mechanism that relies on semantic segmentation and object-centric RoI pooling. We show that our approach of training the autonomous system with human advice, grounded in a rich semantic representation, matches or outperforms prior work in terms of control prediction and explanation generation. Our approach also results in more interpretable visual explanations by visualizing object-centric attention maps. We evaluate our approach on a novel driving dataset with ground-truth human explanations, the Berkeley DeepDrive eXplanation (BDD-X) dataset.","PeriodicalId":72253,"journal":{"name":"Applied AI letters","volume":"2 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ail2.56","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46237887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Objective criteria for explanations of machine learning models 解释机器学习模型的客观标准

Applied AI letters Pub Date : 2021-11-23 DOI: 10.1002/ail2.57

Chih-Kuan Yeh, Pradeep Ravikumar

引用次数: 3