Hide-and-Seek: A Template for Explainable AI

Lack of transparency has been the Achilles heal of Neural Networks and their wider adoption in industry. Despite significant interest this shortcoming has not been adequately addressed. This study proposes a novel framework called Hide-and-Seek (HnS) for training Interpretable Neural Networks and establishes a theoretical foundation for exploring and comparing similar ideas. Extensive experimentation indicates that a high degree of interpretability can be imputed into Neural Networks, without sacrificing their predictive power.

[1]  Koray Kavukcuoglu,et al.  Visual Attention , 2020, Computational Models for Cognitive Vision.

[2]  Rudolf Kruse,et al.  Obtaining interpretable fuzzy classification rules from medical data , 1999, Artif. Intell. Medicine.

[3]  Ivan Laptev,et al.  Is object localization for free? - Weakly-supervised learning with convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Been Kim,et al.  Sanity Checks for Saliency Maps , 2018, NeurIPS.

[5]  Joanna Bryson,et al.  Standardizing Ethical Design for Artificial Intelligence and Autonomous Systems , 2017, Computer.

[6]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[7]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[8]  J. Flickinger,et al.  Machine Learning Approaches for Predicting Radiation Therapy Outcomes: A Clinician's Perspective. , 2015, International journal of radiation oncology, biology, physics.

[9]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

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

[11]  Ronan Collobert,et al.  From image-level to pixel-level labeling with Convolutional Networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Patrick Lin,et al.  Robot Ethics 2.0: From Autonomous Cars to Artificial Intelligence , 2017 .

[13]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[14]  Andreas Stafylopatis,et al.  High-Resolution Class Activation Mapping , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[15]  Abubakar Abid,et al.  Interpretation of Neural Networks is Fragile , 2017, AAAI.

[16]  Guillaume Lample,et al.  Phrase-Based & Neural Unsupervised Machine Translation , 2018, EMNLP.

[17]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Matthijs Douze,et al.  Fixing the train-test resolution discrepancy , 2019, NeurIPS.

[19]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[20]  Gabriel J. Brostow,et al.  Becoming the expert - interactive multi-class machine teaching , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Jasjit S Suri,et al.  State-of-the-art review on deep learning in medical imaging. , 2019, Frontiers in bioscience.

[22]  C. Allen,et al.  Artificial Morality: Top-down, Bottom-up, and Hybrid Approaches , 2005, Ethics and Information Technology.

[23]  Vince D. Calhoun,et al.  Deep learning for neuroimaging: a validation study , 2013, Front. Neurosci..

[24]  Bin Li,et al.  Applications of machine learning in drug discovery and development , 2019, Nature Reviews Drug Discovery.

[25]  Shawn D. Newsam,et al.  Improving Semantic Segmentation via Video Propagation and Label Relaxation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Kouichi Sakurai,et al.  One Pixel Attack for Fooling Deep Neural Networks , 2017, IEEE Transactions on Evolutionary Computation.

[27]  Derek Hoiem,et al.  Diagnosing Error in Object Detectors , 2012, ECCV.

[28]  Andreas Stafylopatis,et al.  Deep neural architectures for prediction in healthcare , 2017, Complex & Intelligent Systems.

[29]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[30]  Michael A. Rupp,et al.  Intelligent Agent Transparency in Human–Agent Teaming for Multi-UxV Management , 2016, Hum. Factors.

[31]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[32]  Wendell Wallach,et al.  Why Machine Ethics? , 2006, IEEE Intelligent Systems.

[33]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[34]  Michael Anderson,et al.  Machine Ethics , 2011 .

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

[36]  Ananthram Swami,et al.  Practical Black-Box Attacks against Machine Learning , 2016, AsiaCCS.

[37]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[38]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[39]  Peter W. Glynn,et al.  Likelihood ratio gradient estimation for stochastic systems , 1990, CACM.

[40]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

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

[42]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[43]  John D. Lee,et al.  Human-Automation Collaboration in Dynamic Mission Planning: A Challenge Requiring an Ecological Approach , 2006 .

[44]  Thomas Richardson,et al.  Interpretable Boosted Naïve Bayes Classification , 1998, KDD.

[45]  Yang Zhang,et al.  A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations , 2018, ICML.

[46]  Pamela J. Hinds,et al.  Autonomy and Common Ground in Human-Robot Interaction: A Field Study , 2007, IEEE Intelligent Systems.

[47]  Alex Zhavoronkov,et al.  Applications of Deep Learning in Biomedicine. , 2016, Molecular pharmaceutics.

[48]  Abbe Mowshowitz,et al.  Bias on the web , 2002, CACM.

[49]  Geraint Rees,et al.  Clinically applicable deep learning for diagnosis and referral in retinal disease , 2018, Nature Medicine.

[50]  Yoshua Bengio,et al.  Hierarchical Multiscale Recurrent Neural Networks , 2016, ICLR.

[51]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[52]  Dumitru Erhan,et al.  The (Un)reliability of saliency methods , 2017, Explainable AI.

[53]  Andrea Vedaldi,et al.  Salient Deconvolutional Networks , 2016, ECCV.

[54]  Yiming Yang,et al.  XLNet: Generalized Autoregressive Pretraining for Language Understanding , 2019, NeurIPS.

[55]  Tim Miller,et al.  Explanation in Artificial Intelligence: Insights from the Social Sciences , 2017, Artif. Intell..

[56]  Chris Yakopcic,et al.  A State-of-the-Art Survey on Deep Learning Theory and Architectures , 2019, Electronics.

[57]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[58]  J. Murphy.  The General Data Protection Regulation (GDPR) , 2018, Irish medical journal.

[59]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[60]  Jack P. C. Kleijnen,et al.  Optimization and Sensitivity Analysis of Computer Simulation Models by the Score Function Method , 1996 .

[61]  Ankur Taly,et al.  Axiomatic Attribution for Deep Networks , 2017, ICML.

[62]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[63]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[64]  Adam Tauman Kalai,et al.  Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings , 2016, NIPS.

[65]  Ivan Bratko,et al.  Machine Learning: Between Accuracy and Interpretability , 1997 .

[66]  Bradley Hayes,et al.  Improving Robot Controller Transparency Through Autonomous Policy Explanation , 2017, 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI.