A 57 mW 12.5 μj/epoch embedded mixed-mode neuro-fuzzy processor for mobile real-time object recognition

IEEE Journal of Solid-State Circuits

Volumn 48, Issue 11, 2013, Pages 2894-2907

  Oh, Jinwook ^a   Kim, Gyeonghoon ^a   Nam, Byeong Gyu ^a   Yoo, Hoi Jun ^a  

^a Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

Author keywords

A D; analog digital mixed mode; fuzzy logic; learning based calibration; low power; mixed mode processor; mobile; neural network; neuro fuzzy; object recognition; on line learning; real time

Indexed keywords

A/D; LOW POWER; MIXED MODE; MOBILE; NEURO-FUZZY; ONLINE LEARNING; REAL-TIME;

ASYNCHRONOUS SEQUENTIAL LOGIC; CALIBRATION; E-LEARNING; ENERGY EFFICIENCY; FLEXIBLE ELECTRONICS; FUZZY LOGIC; FUZZY SYSTEMS; NEURAL NETWORKS; OBJECT RECOGNITION;

PIPELINE PROCESSING SYSTEMS;

EID: 84887321418     PISSN: 00189200     EISSN: None     Source Type: Journal    
DOI: 10.1109/JSSC.2013.2280238     Document Type: Article

References (29)

1. S. Lee et al., "A 345 mW heterogeneous many-core processor with an intelligent inference engine for robust object recognition," IEEE J. Solid-State Circuits, vol. 46, no. 1, pp. 42-51, Jan. 2011.
2. G. Karthikeyan et al., "Development of Brain-Computer Interface (BCI) model for real-time applications using DSP processors," in Proc. IEEE Neural Engineering, Apr. 2009, pp. 419-422.
3. J.-Y. Kimet al., "A 201.4 GOPS 496mWreal-timemulti-object recognition processor with bio-inspired neural perception engine," IEEE J. Solid-State Circuits, vol. 45, no. 1, pp. 32-45, Jan. 2010.
4. K. S. Ray et al., "Neuro-fuzzy reasoning for occluded object recognition," Fuzzy Sets and Systems, vol. 94, no. 1, pp. 1-28, 1998. (Pubitemid 128654770)
5. J. Oh et al., "A 1.2-mW online learning mixed-mode intelligent inference engine for low power real-time object recognition processor," IEEE Trans. Very Large Scale Integration (VLSI) Syst., vol. 21, no. 5, pp. 921-933, 2013.
6. D. Strigl et al., "Performance and scalability of GPU-based convolutional neural networks," IEEE Parallel, Distributed and Network-Based Processing, pp. 317-324, Feb. 2010.
7. K. L. Rice et al., "GPGPU acceleration of cellular simultaneous recurrent networks adapted for maze traversals," in Proc. IEEE Int. Joint Conf. Neural Networks, 2011, pp. 317-324.
8. B. J. Sheu et al., "Neuromorphic models on a GPGPU cluster," in Proc. IEEE In. Joint Conf. Neural Networks, Jul. 2010, pp. 1-8.
9. H. Graf et al., "A massively parallel digital learning processor," in Proc. Adv. Neural Information Processing Syst., 2009, pp. 529-536.
10. H. M. Abbas et al., "Performance of the Alex AVX-2 MIMD architecture in learning rate NetTalk database," IEEE Trans. Neural Networks, vol. 15, pp. 505-514, 2004.
11. J. Oh et al., "A 57 mWembeddedmixed-mode neuro-fuzzy accelerator for intelligent multi-core processor," in IEEE Int. Solid-State Circuits Conf. (ISSCC) Dig. Tech. Papers, 2011, pp. 130-131.
12. J.-S.-R. Jang et al., "ANFIS: Adaptive-network-based fuzzy inference system," IEEE Trans. Syst., Man Cybern., vol. 23, pp. 665-685, 1993.
13. H. Ying, "Interval type-2 Takagi-Sugeno fuzzy systems with linear rule consequent are universal approximators," North American Fuzzy Information Processing Society, pp. 1-5, 2009.
14. J. R. Brown et al., "Artificial neural network on a SIMD architecture," in Proc. Frontiers of Massively Parallel Computation, Oct. 1998, pp. 43-47.
15. J. Clemons et al., "MEVBench: A mobile computer vision benchmarking suite," in IEEE Int. Conf. Workload Characterization (IISWC), 2011, pp. 91-102.
16. S. R. Chowdhury and H. Saha, "A high performance FPGA-based fuzzy processor architecture for medical diagnosis," IEEE Micro, vol. 28, no. 5, pp. 38-52, 2008.
17. V. Salapura et al., "A fuzzy RISC processor," IEEE Trans. Fuzzy Syst., vol. 8, pp. 781-790, 2000. (Pubitemid 33777806)
18. S. Guo et al., "Design application of an analog fuzzy logic controller," IEEE Trans. Fuzzy Syst., pp. 429-438, 1996. (Pubitemid 126785334)
19. W. Wang et al., "Neuro-fuzzy system with high-speed low-power analog blocks," Fuzzy Sets . Syst., vol. 157, pp. 2974-2982, 2006. (Pubitemid 44528753)
20. F. V. Verdu et al., "A Design approach or analog neuro/fuzzy systems in CMOS digital technologies," Computer Electronics and Engineering, vol. 25, pp. 309-337, 1999.
21. S.-H. Hwang et al., "A high-speed fuzzy inference processor for trapezoid-shaped membership functions," J. Information Science and Engineering, vol. 21, pp. 607-626, 2005.
22. A. F. Gobi et al., "The potential of fuzzy neural networks in the realization of approximate reasoning engines," Fuzzy Sets and Systems, vol. 157, pp. 2954-2973, 2006. (Pubitemid 44528752)
23. M. Yutaka and M. Wakamura, "Simultaneous perturbation learning rule for recurrent neural networks and its FPGA implementation," IEEE Trans. Neural Networks, vol. 16, no. 6, pp. 1664-1672, 2005. (Pubitemid 41714996)
24. B. E. Boser et al., "An analog neural network processor with programmable topology," IEEE J. Solid-State Circuits, vol. 26, no. 12, pp. 2017-2025, Jan. 1991.
25. V. Karkare et al., "A 75 W, 16-channel neural spike-sorting processor with unsupervised clustering," in Proc. IEEE Symp. VLSI Circuits, 2011, pp. 252-253.
26. J. Oh et al., "An asynchronous mixed-mode neuro-fuzzy controller for energy efficient machine intelligence SoC," in Proc. IEEE Asian Solid-State Circuits Conf., Nov. 2011, pp. 389-392.
27. P. R. Kinget et al., "Device mismatch and tradeoffs in the design of analog circuits," IEEE J. Solid-State Circuits, vol. 50, no. 6, pp. 1212-1224, Jan. 2005. (Pubitemid 40819363)
28. J. Marku et al., "Current mismatch and nonlinearity compensation in mixed-mode array processor," in Proc. Int. Workshop on Cellular Neural Networks and Their Applications, 2008, pp. 75-80.
29. "OMAP4430 Processor Technical Reference Manual, Ver. AN," Texas Instrum. [Online]. Available: http://www.ti.com/product/omap4430