Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units

In this paper, we introduce the concept of Prior Activation Distribution (PAD) as a versatile and general technique to capture the typical activation patterns of hidden layer units of a Deep Neural Network used for classification tasks. We show that the combined neural activations of such a hidden layer have class-specific distributional properties, and then define multiple statistical measures to compute how far a test sample's activations deviate from such distributions. Using a variety of benchmark datasets (including MNIST, CIFAR10, Fashion-MNIST & notMNIST), we show how such PAD-based measures can be used, independent of any training technique, to (a) derive fine-grained uncertainty estimates for inferences; (b) provide inferencing accuracy competitive with alternatives that require execution of the full pipeline, and (c) reliably isolate out-of-distribution test samples.

[1]  Charles Blundell,et al.  Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles , 2016, NIPS.

[2]  Yoshua Bengio,et al.  Understanding intermediate layers using linear classifier probes , 2016, ICLR.

[3]  Edward H. Shortliffe,et al.  The Dempster-Shafer theory of evidence , 1990 .

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

[5]  Pieter Abbeel,et al.  Benchmarking Deep Reinforcement Learning for Continuous Control , 2016, ICML.

[6]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  M. Artés.  Statistical errors. , 1977, Medicina clinica.

[8]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[9]  Zoubin Ghahramani,et al.  Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference , 2015, ArXiv.

[10]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[11]  Murat Sensoy,et al.  Evidential Deep Learning to Quantify Classification Uncertainty , 2018, NeurIPS.

[12]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[13]  Christopher K. I. Williams.  Computing with Infinite Networks , 1996, NIPS.

[14]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[15]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[16]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[17]  David Mackay,et al.  Probable networks and plausible predictions - a review of practical Bayesian methods for supervised neural networks , 1995 .

[18]  Bolei Zhou,et al.  Network Dissection: Quantifying Interpretability of Deep Visual Representations , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Stefan M. Herzog,et al.  Experimental biology: Sometimes Bayesian statistics are better , 2013, Nature.

[20]  John D. Hunter,et al.  Matplotlib: A 2D Graphics Environment , 2007, Computing in Science & Engineering.

[21]  Timo Aila,et al.  Pruning Convolutional Neural Networks for Resource Efficient Inference , 2016, ICLR.

[22]  Jelena Frtunikj,et al.  Deep Learning for Self-Driving Cars: Chances and Challenges , 2018, 2018 IEEE/ACM 1st International Workshop on Software Engineering for AI in Autonomous Systems (SEFAIAS).

[23]  Kevin Smith,et al.  Bayesian Uncertainty Estimation for Batch Normalized Deep Networks , 2018, ICML.

[24]  Max Welling,et al.  Multiplicative Normalizing Flows for Variational Bayesian Neural Networks , 2017, ICML.

[25]  Abhinav Gupta,et al.  Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[26]  H. N. Io,et al.  Chatbots and conversational agents: A bibliometric analysis , 2017, 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM).

[27]  Pradeep Ravikumar,et al.  Representer Point Selection for Explaining Deep Neural Networks , 2018, NeurIPS.

[28]  David Barber,et al.  A Scalable Laplace Approximation for Neural Networks , 2018, ICLR.

[29]  Albin Cassirer,et al.  Randomized Prior Functions for Deep Reinforcement Learning , 2018, NeurIPS.

[30]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[31]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[32]  Xiang Li,et al.  Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

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

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

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

[37]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[38]  Jascha Sohl-Dickstein,et al.  SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability , 2017, NIPS.

[39]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[40]  Yarin Gal,et al.  Uncertainty in Deep Learning , 2016 .

[41]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[42]  Wonyong Sung,et al.  Structured Pruning of Deep Convolutional Neural Networks , 2015, ACM J. Emerg. Technol. Comput. Syst..

[43]  Tarek F. Abdelzaher,et al.  DeepIoT: Compressing Deep Neural Network Structures for Sensing Systems with a Compressor-Critic Framework , 2017, SenSys.

[44]  Ryan P. Adams,et al.  Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks , 2015, ICML.

[45]  Alex Graves,et al.  Practical Variational Inference for Neural Networks , 2011, NIPS.