Efficient On-Line Error Detection and Mitigation for Deep Neural Network Accelerators

The use of deep neural network accelerators in safety-critical systems, for example autonomous vehicles, requires measures to ensure functional safety of the embedded hardware. However, due to the vast computational requirements that deep neural networks exhibit, the use of traditional redundancy-based approaches for the detection and mitigation of random hardware errors leads to very inefficient systems. In this paper we present an efficient and effective method to detect critical bit-flip errors in neural network accelerators and mitigate their effect at run time. Our method is based on an anomaly detection in the intermediate outputs of the neural network. We evaluate our method by performing fault injection simulations with two deep neural networks and data sets. In these experiments our error detector achieves a recall of up to 99.03% and a precision of up to 97.29%, while requiring a computation overhead of only 2.67% or less.

[1]  Andrea Bernieri,et al.  On-line fault detection and diagnosis obtained by implementing neural algorithms on a digital signal processor , 1996 .

[2]  Philipp Gysel,et al.  Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks , 2016, ArXiv.

[3]  Norbert Wehn,et al.  Reliable on-chip systems in the nano-era: Lessons learnt and future trends , 2013, 2013 50th ACM/EDAC/IEEE Design Automation Conference (DAC).

[4]  Gerd Ascheid,et al.  Accurate neuron resilience prediction for a flexible reliability management in neural network accelerators , 2018, 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[5]  Geoffrey E. Hinton,et al.  On rectified linear units for speech processing , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

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

[7]  R. Aitken,et al.  Reliability analysis reloaded: How will we survive? , 2013, 2013 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[8]  Sherief Reda,et al.  Understanding the impact of precision quantization on the accuracy and energy of neural networks , 2016, Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017.

[9]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Gerd Ascheid,et al.  Efficient Stochastic Inference of Bitwise Deep Neural Networks , 2016, ArXiv.

[11]  Ran El-Yaniv,et al.  Binarized Neural Networks , 2016, ArXiv.

[12]  Jan Hendrik Metzen,et al.  On Detecting Adversarial Perturbations , 2017, ICLR.

[13]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[14]  Simon Burton,et al.  Making the Case for Safety of Machine Learning in Highly Automated Driving , 2017, SAFECOMP Workshops.

[15]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[16]  Johannes Stallkamp,et al.  Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition , 2012, Neural Networks.

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

[18]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[19]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[20]  Vivienne Sze,et al.  Using Dataflow to Optimize Energy Efficiency of Deep Neural Network Accelerators , 2017, IEEE Micro.

[21]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[22]  Tianshi Chen,et al.  ShiDianNao: Shifting vision processing closer to the sensor , 2015, 2015 ACM/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA).

[23]  Joel Emer,et al.  Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks , 2016, CARN.

[24]  Guanpeng Li,et al.  Understanding Error Propagation in Deep Learning Neural Network (DNN) Accelerators and Applications , 2017, SC17: International Conference for High Performance Computing, Networking, Storage and Analysis.

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

[26]  Henk Corporaal,et al.  Memory-centric accelerator design for Convolutional Neural Networks , 2013, 2013 IEEE 31st International Conference on Computer Design (ICCD).

[27]  E. Ibe,et al.  Impact of Scaling on Neutron-Induced Soft Error in SRAMs From a 250 nm to a 22 nm Design Rule , 2010, IEEE Transactions on Electron Devices.

[28]  Eugenio Culurciello,et al.  An Analysis of Deep Neural Network Models for Practical Applications , 2016, ArXiv.

[29]  Pritish Narayanan,et al.  Deep Learning with Limited Numerical Precision , 2015, ICML.

[30]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..