Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

IEEE Access - Tập 6 - Trang 52138-52160 - 2018
Amina Adadi1,2, Mohammed Berrada1
1Computer and Interdisciplinary Physics Laboratory, Sidi Mohammed Ben Abdellah University, Fez, Morocco
2ORCiD

Tóm tắt

Từ khóa


Tài liệu tham khảo

fox, 2017, Explainable planning, Proc IJCAI Workshop, 24

10.1109/ICRA.2017.7989155

10.24963/ijcai.2017/23

harbers, 0, Self-explaining agents in virtual training

10.1109/WI-IAT.2010.115

10.1109/ACIIW.2017.8272595

langley, 2017, Explainable agency for intelligent autonomous systems, Proc AAAI, 4762, 10.1609/aaai.v31i2.19108

garcia, 2018, Explain yourself: A natural language interface for scrutable autonomous robots, HRI Workshop on Explainable Robotic Systems

neerincx, 2018, Using perceptual and cognitive explanations for enhanced human-agent team performance, Proc Int Conf Eng Psychol Cognit Ergonom, 204, 10.1007/978-3-319-91122-9_18

puri, 2017, MAGIX Model agnostic globally interpretable explanations

varshney, 2018, Why interpretability in machine learning? An answer using distributed detection and data fusion theory

2016, European Union’s General Data Protection Regulation

10.1109/ARSO.2017.8025197

miller, 2017, Explanation in Artificial Intelligence Insights from the Social Sciences

10.1007/978-3-319-25127-1_4

danjuma, 2015, Performance Evaluation of Machine Learning Algorithms in Post-operative Life Expectancy in the Lung Cancer Patients

dignum, 2017, Responsible artificial intelligence: Designing AI for human values, ITU J ICT Discoveries, 1, 1

10.1145/2783258.2788613

10.1007/s00146-016-0651-x

baum, 2017, A survey of artificial general intelligence projects for ethics risk and policy

prabhakar, 2017, Powerful but limited: A DARPA perspective on AI, Proc DARPA

igami, 2017, Artificial intelligence as structural estimation Economic interpretations of deep blue bonanza and AlphaGo

weld, 2018, The challenge of crafting intelligible intelligence

piltaver, 2014, Comprehensibility of classification trees—Survey design validation, Proc ITI, 5

akyol, 2016, Price of transparency in strategic machine learning

10.5381/jot.2010.9.3.a3

van lent, 2004, An explainable artificial intelligence system for small-unit tactical behavior, Proc Conf Innov Appl Artif Intell, 900

doran, 2017, What Does Explainable AI Really Mean? A New Conceptualization of Perspectives

swartout, 1988, Explanation in expert systems: A survey

bojarski, 2017, Explaining how a deep neural network trained with end-to-end learning steers a car

koh, 2017, Understanding black-box predictions via influence functions

lundberg, 2017, A unified approach to interpreting model predictions, Proc Adv Neural Inf Process Syst, 4768

10.1109/CIDM.2013.6597210

10.24963/ijcai.2017/371

lipton, 2016, The mythos of model interpretability, Proc ICML Workshop Human Interpret Mach Learn, 96

howell, 2018, A framework for addressing fairness in consequential machine learning, Proc FAT Conf Tuts, 1

10.1111/1745-9133.12047

gilpin, 2018, Explaining explanations An approach to evaluating interpretability of machine learning

paul, 2016, Interpretable machine learning: Lessons from topic modeling, Proc CHI Workshop Hum -Centered Mach Learn, 1

10.1145/1040830.1040911

miller, 2017, Explainable AI: Beware of inmates running the asylum, Proc Workshop Explainable AI (XAI) IJCAI, 36

10.1109/CIDM.2013.6597212

10.1109/CVPR.2017.354

poursabzi-sangdeh, 2018, Manipulating and measuring model interpretability

10.1007/978-3-319-54024-5_5

mishra, 2017, Local interpretable model-agnostic explanations for music content analysis, Proc ISMIR, 537

mohseni, 2018, A human-grounded evaluation benchmark for local explanations of machine learning

10.1016/j.dss.2010.12.003

hall, 2018, An Introduction to Machine Learning Interpretability

tan, 2015, Improving the interpretability of deep neural networks with stimulated learning, Proc IEEE Workshop Autom Speech Recognition Understanding (ASRU), 617

10.1002/isaf.1422

kass, 1988, The need for user models in generating expert system explanations

2017, Unfairness by Algorithm Distilling the Harms of Automated Decision-Making

henelius, 2017, Interpreting classifiers through attribute interactions in datasets

knight, 2017, The U S military wants its autonomous machines to explain themselves

2018, Equifax Launches NeuroDecision Technology

silver, 2017, Mastering the game of go without human knowledge, Nature, 550, 354, 10.1038/nature24270

dhurandhar, 2017, TIP Typifying the interpretability of procedures

10.1177/1745691617693393

10.1214/10-STS330

10.1145/2783258.2783407

offert, 2017, ‘I know it when I see it’ Visualization and intuitive interpretability

10.1145/2856767.2856811

10.1109/VLHCC.2013.6645235

10.1145/2166966.2166996

barocas, 2018, The FAT-ML Workshop Series on Fairness Accountability and Transparency in Machine Learning

2017, Top 10 strategic technology trends for 2018

wilson, 0, Proceedings of NIPS 2016 Workshop on Interpretable Machine Learning for Complex Systems

kim, 0, 2018 Workshop on Human Interpretability in Machine Learning (WHI)

hohman, 2018, Visual Analytics in Deep Learning An Interrogative Survey for the Next Frontiers

farina, 2017, Proc XCI Explainable Comput Intell Workshop

tan, 2018, Detecting Bias in Black-Box Models Using Transparent Model Distillation

aha, 2017, Proc Workshop Explainable AI (XAI) IJCAI

zhu, 2018, Explainable AI for designers: A human-centered perspective on mixed-initiative co-creation, Proc IEEE Conf Comput Intell Games (CIG), 458

tamagnini, 2017, Interpreting black-box classifiers using instance-level visual explanations, Proc 2nd Workshop Hum -Loop Data Anal, 10.1145/3077257.3077260

guyon, 2017, Proc IJCNN Explainability Learn Mach

katuwal, 2016, Machine learning model interpretability for precision medicine

holzinger, 2017, What do we need to build explainable AI systems for the medical domain?

lightbourne, 2017, Damned lies & criminal sentencing using evidence-based tools, 327

che, 2017, Interpretable deep models for ICU outcome prediction, Proc AMIA Annu Symp, 371

mcfarland, 2018, Uber Shuts Down Self-Driving Operations in Arizona CNN

norvig, 2018, Google’s approach to artificial intelligence and machine learning

haspiel, 2018, Explanations and Expectations Trust Building in Automated Vehicles deepblue lib umich edu

bojarski, 2016, End to End Learning for Self-Driving Cars

tan, 2018, Transparent model distillation

tan, 2018, Auditing black-box models using transparent model distillation with side information

tan, 2017, Interpretable approaches to detect bias in black-box models, Proc AAAI/ACM Conf AI Ethics Soc, 1

xu, 2018, Interpreting deep classifier by visual distillation of dark knowledge

mikolov, 2013, Distributed representations of words and phrases and their compositionality, Proc Adv Neural Inf Process Syst (NIPS), 3111

10.1109/CVPR.2015.7299155

10.1016/j.ins.2012.10.039

10.1109/TCDS.2016.2628365

zhang, 2016, A sensitivity analysis of (and practitioners’ Guide to) convolutional neural networks for sentence classification

10.1214/ss/1009213726

palm, 2017, Recurrent relational networks for complex relational reasoning

10.1109/CIDM.2011.5949423

10.1109/CVPR.2017.110

ras, 2018, Explanation methods in deep learning Users values concerns and challenges

santoro, 2017, A simple neural network module for relational reasoning

10.1214/11-AOAS495

kim, 2014, The Bayesian case model: A generative approach for case-based reasoning and prototype classification, Proc Adv Neural Inf Process Syst, 1952

10.1371/journal.pone.0130140

louizos, 2017, Causal effect inference with deep latent-variable models, Proc Adv Neural Inf Process Syst (NIPS), 6446

fisher, 2018, Model class reliance Variable importance measures for any machine learning model class from the ‘rashomon’ perspective

goudet, 2017, Learning functional causal models with generative neural networks

kim, 2016, Examples are not enough, learn to criticize! criticism for interpretability, Proc 29th Conf Neural Inf Process Syst (NIPS), 2280

gurumoorthy, 2017, ProtoDash Fast interpretable prototype selection

yuan, 2017, Adversarial examples Attacks and defenses for deep learning

wachter, 2017, Counterfactual Explanations Without Opening the Black Box Automated Decisions and the GDPR

breiman, 2001, Statistical Modeling The Two Cultures Statistical Science

10.1109/TITB.2006.880553

doshi-velez, 2018, Towards a rigorous science of interpretable machine learning

10.1145/3173574.3174156

guidotti, 2018, A survey of methods for explaining black box models

10.23919/MIPRO.2018.8400040

hara, 2016, Making Tree Ensembles Interpretable

10.1145/2601248.2601268

tan, 2016, Tree space prototypes Another look at making tree ensembles interpretable

10.1214/15-AOAS848

10.4088/JCP.12m08338

xu, 2015, Show, attend and tell: Neural image caption generation with visual attention, Proc Int Conf Mach Learn (ICML), 1

10.1016/j.asoc.2009.04.004

10.1007/s10994-015-5528-6

wang, 2015, Falling rule lists, Proc 14th Int Conf Artif Intell Statist (AISTATS), 1013

2018, Revenues From the Artificial Intelligence (AI) Market Worldwide From 2016 to 2025

sarkar, 2016, Accuracy and interpretability trade-offs in machine learning applied to safer gambling, Proc CEUR Workshop, 79

su, 2015, Interpretable two-level Boolean rule learning for classification

2018, Worldwide Semiannual Cognitive Artificial Intelligence Systems Spending Guide

10.1214/09-AOAS285

10.1109/ICIP.2016.7532763

green, 2010, Modeling heterogeneous treatment effects in large-scale experiments using Bayesian additive regression trees, Proc Summer Meeting Soc Political Methodol, 1

10.1016/j.patcog.2016.11.008

thiagarajan, 2016, TreeView Peeking into deep neural networks via feature-space partitioning

10.1109/TKDE.2007.190734

bastani, 2017, Interpretability via model extraction

smilkov, 2017, SmoothGrad Removing noise by adding noise

molnar, 2018, Interpretable Machine Learning A Guide for Making Black Box Models Explainable

sundararajan, 2017, Axiomatic Attribution for Deep Networks

10.1145/3109859.3109890

10.1109/CVPR.2016.319

linsley, 2018, Global-and-local attention networks for visual recognition

guidotti, 2018, Local rule-based explanations of black box decision systems

welling, 2016, Forest floor visualizations of random forests

10.1080/10618600.2014.907095

10.1111/j.1365-2656.2008.01390.x

kindermans, 2018, Learning how to explain neural networks: PatternNet and patternAttribution, Proc Int Conf Learn Represent, 1

shrikumar, 2016, Not just a black box Interpretable deep learning by propagating activation differences

10.1109/ICCV.2017.371

dabkowski, 2017, Real time image saliency for black box classifiers, Proc Adv Neural Inf Process Syst, 6970

chander, 2018, Proc MAKE-Explainable AI

biundo, 2018, Proc ICAPS Workshop EXplainable AI Planning

graaf, 2018, HRI Workshop on Explainable Robotic Systems

komatsu, 2018, Proc ACM Intell Interfaces (IUI) Workshop Explainable Smart Syst (EXSS)

alonso, 2018, Proc IPMU Adv Explainable Artif Intell

agudo, 2018, Proc ICCBR 1st Workshop Case-Based Reasoning Explanation Intell Syst (XCBR)

10.5121/ijdkp.2014.4302

gunning, 2018, Explainable artificial intelligence (xai)

nguyen, 2016, Synthesizing the preferred inputs for neurons in neural networks via deep generator networks, Proc Adv Neural Inf Process Syst (NIPS), 3387

10.1016/0950-7051(96)81920-4

hall, 2018, Using H2O Driverless AI H2O AI

valenzuela-escárcega, 2018, Lightly-supervised representation learning with global interpretability

2018, Cognilytica’s AI Positioning Matrix (CAPM)

10.1145/2939672.2939778

10.1109/TNN.2005.863472

2018, Explainable Machine Learning Challenge

erhan, 2010, Understanding representations learned in deep architectures

johansson, 2004, The truth is in there—Rule extraction from opaque models using genetic programming, Proc FLAIRS Conf, 658

casalicchio, 2018, Visualizing the feature importance for black box models

hailesilassie, 2017, Rule extraction algorithm for deep neural networks A review

yang, 2018, Global model interpretation via recursive partitioning

10.1007/978-3-540-72393-6_139

barakat, 2005, Eclectic rule-extraction from support vector machines, Int J Comput Intell, 2, 59

zeiler, 2014, Visualizing and understanding convolutional networks, Proc Eur Conf Comput Vis, 818

sadowski, 2015, Deep learning, dark knowledge, and dark matter, Proc NIPS Workshop High-Energy Phys Mach Learn (PMLR), 42, 81

hinton, 2015, Distilling the knowledge in a neural network

che, 2015, Distilling knowledge from deep networks with applications to healthcare domain

ribeiro, 2018, Anchors: High-precision model-agnostic explanations, Proc AAAI Conf Artif Intell, 1

10.1080/01621459.2017.1307116

baehrens, 2010, How to explain individual classification decisions, J Mach Learn Res, 11, 1803

simonyan, 2013, Deep Inside Convolutional Networks Visualising Image Classification Models and Saliency Maps