A general approach to compute the relevance of middle-level input features

This work proposes a novel general framework, in the context of eXplainable Artificial Intelligence (XAI), to construct explanations for the behaviour of Machine Learning (ML) models in terms of middle-level features. One can isolate two different ways to provide explanations in the context of XAI: low and middle-level explanations. Middle-level explanations have been introduced for alleviating some deficiencies of low-level explanations such as, in the context of image classification, the fact that human users are left with a significant interpretive burden: starting from low-level explanations, one has to identify properties of the overall input that are perceptually salient for the human visual system. However, a general approach to correctly evaluate the elements of middle-level explanations with respect ML model responses has never been proposed in the literature.

[1]  Carlos Guestrin,et al.  Anchors: High-Precision Model-Agnostic Explanations , 2018, AAAI.

[2]  Francis R. Bach,et al.  Structured Sparse Principal Component Analysis , 2009, AISTATS.

[3]  Thomas Brox,et al.  Synthesizing the preferred inputs for neurons in neural networks via deep generator networks , 2016, NIPS.

[4]  Franco Turini,et al.  Local Rule-Based Explanations of Black Box Decision Systems , 2018, ArXiv.

[5]  Pascal Vincent,et al.  Visualizing Higher-Layer Features of a Deep Network , 2009 .

[6]  Stefano Soatto,et al.  Quick Shift and Kernel Methods for Mode Seeking , 2008, ECCV.

[7]  Francesco Isgrò,et al.  Contrastive Explanations to Classification Systems Using Sparse Dictionaries , 2019, ICIAP.

[8]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[9]  Seong Joon Oh,et al.  Towards Reverse-Engineering Black-Box Neural Networks , 2017, ICLR.

[10]  Jude W. Shavlik,et al.  in Advances in Neural Information Processing , 1996 .

[11]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[12]  Alberto Finzi,et al.  Learning attentional regulations for structured tasks execution in robotic cognitive control , 2019, Autonomous Robots.

[13]  Charles Richter,et al.  Bayesian Learning for Safe High-Speed Navigation in Unknown Environments , 2015, ISRR.

[14]  A Apicella,et al.  Middle-Level Features for the Explanation of Classification Systems by Sparse Dictionary Methods , 2020, Int. J. Neural Syst..

[15]  Lalana Kagal,et al.  Explaining Explanations: An Overview of Interpretability of Machine Learning , 2018, 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA).

[16]  Wojciech Samek,et al.  Methods for interpreting and understanding deep neural networks , 2017, Digit. Signal Process..

[17]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[18]  Xun Xue,et al.  A Survey of Data-Driven and Knowledge-Aware eXplainable AI , 2020, IEEE Transactions on Knowledge and Data Engineering.

[19]  Cynthia Rudin,et al.  Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model , 2015, ArXiv.

[20]  Roberto Prevete,et al.  Designing Structured Sparse Dictionaries for Sparse Representation Modeling , 2011, Computer Recognition Systems 4.

[21]  Francesco Isgrò,et al.  Sparse Dictionaries for the Explanation of Classification Systems , 2019, PIE@CAiSE.

[22]  Jason Yosinski,et al.  Understanding Neural Networks via Feature Visualization: A survey , 2019, Explainable AI.

[23]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[24]  Alexander Binder,et al.  Evaluating the Visualization of What a Deep Neural Network Has Learned , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[25]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[26]  Honglak Lee,et al.  An Analysis of Single-Layer Networks in Unsupervised Feature Learning , 2011, AISTATS.

[27]  Quanshi Zhang,et al.  Visual interpretability for deep learning: a survey , 2018, Frontiers of Information Technology & Electronic Engineering.

[28]  Sebastián Ventura,et al.  Performing Multi-Target Regression via a Parameter Sharing-Based Deep Network , 2019, Int. J. Neural Syst..

[29]  Franco Turini,et al.  A Survey of Methods for Explaining Black Box Models , 2018, ACM Comput. Surv..

[30]  Michael J. Lyons,et al.  Coding facial expressions with Gabor wavelets , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[31]  A. Apicella,et al.  Explaining classification systems using sparse dictionaries , 2019, ESANN.

[32]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[33]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.