Cognitive computing safety: The new horizon for reliability / the design and evolution of deep learning workloads

IEEE Micro

Volumn 37, Issue 1, 2017, Pages 15-21

  Zhu, Yuhao ^a   Reddi, Vijay Janapa ^a   Adolf, Robert ^b   Rama, Saketh ^b   Reagen, Brandon ^b   Wei, Gu Yeon ^b   Brooks, David ^b  

^a UNIVERSITY OF TEXAS AT AUSTIN   (United States)

^b HARVARD UNIVERSITY   (United States)

Author keywords

cognitive architectures; deep learning; Fathom

Indexed keywords

HARDWARE; MICROWAVE INTEGRATED CIRCUITS;

COGNITIVE ARCHITECTURES; COGNITIVE COMPUTING; FATHOM; POSITION PAPERS;

DEEP LEARNING;

EID: 85015424903     PISSN: 02721732     EISSN: None     Source Type: Journal    
DOI: 10.1109/MM.2017.2     Document Type: Article

References (18)

1. J. Dean and L.A. Barroso, "The Tail at Scale," Comm. ACM, vol. 56, no. 2, 2013, pp. 74-80.
2. J. Golson, "Tesla Driver Killed in Crash with Autopilot Active, NHTSA Investigating," Verge, 30 June 2016; www.theverge.com/2016/6/30/1207 2408/teslaautopilot-car-crash-death -autonomous-model-s.
3. "Final Report on the Accident on 1st June 2009 to the Airbus A330-203 Registered FGZCP Operated by Air France Flight AF 447 Rio de Janeiro-Paris," BEA, July 2012.
4. S. Borkar et al., "Parameter Variations and Impact on Circuits and Microarchitecture," Proc. 40th Ann. Design Automation Conf., 2003, pp. 338-342.
5. D.J.Sorin,FaultTolerantComputerArchitecture, MorganandClaypool,2009.
6. J. Chang, G.A. Reis, and D.I. August, "Automatic Instruction-Level Software- Only Recovery," Proc. Int'l Conf. Dependable Systems and Networks, 2006, pp. 83-92.
7. B. Reagen et al., "Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators," Proc. 43rd Int'l Symp. Computer Architecture, 2016, pp. 267-278.
8. S. Han et al., "EIE: Efficient Inference Engine on Compressed Deep Neural Network," Proc. 43rd Int'l Symp. Computer Architecture, 2016, pp. 243-254.
9. J. Yoshida, "ARM Raises Bar for Safety, Determinism," EE Times, 19 Sept. 2016; www.eetimes.com /document.asp?doc id/1330483.
10. O. Temam, "A Defect-Tolerant Accelerator for Emerging High-Performance Applications," Proc. 39th Int'l Symp. Computer Architecture, 2012, pp. 356-367.
11. F. Cristian, "Understanding Fault-Tolerant Distributed Systems," Comm. ACM, vol. 34, 1993, pp. 56-78.
12. T.G. Dietterich, "Ensemble Methods in Machine Learning," Proc. Int'l Workshop Multiple Classifier Systems, 2000, pp. 1-15.
13. D. Beyer, The Future of Machine Intelligence: Perspectives from Leading Practitioners, O'Reilly, 2016.
14. R.P. Pothukuchi et al., "Using Multiple Input, Multiple Output Formal Control to Maximize Resource Efficiency in Architectures," Proc. ACM/IEEE 43rd Ann. Int'l Symp. Computer Architecture, 2016; doi:10.1109/ISCA.2016.63.
15. R. Adolf et al., "Fathom: Reference Workloads for Modern Deep Learning Methods," Proc. IEEE Int'l Symp. Workload Characterization, 2016; doi:10.1109/IISWC.2016.7581275.
16. O. Russakovsky et al., "ImageNet Large Scale Visual Recognition Challenge," Int'l J. Computer Vision, vol. 115, no. 3, 2014, pp. 211-252.
17. A. Krizhevsky, I. Sutskever, and G.E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Advances in Neural Information Processing Systems (NIPS), 2012, pp. 1097-1105.
18. R. Adolf et al., "Fathom: Reference Workloads for Modern Deep Learning Methods," Proc. IEEE Int'l Symp. Workload Characterization (IISWC), 2016, pp. 1-10.