Non-Boolean Associative Processing: Circuits, System Architecture, and Algorithms

被引:9
作者
Fang, Yan [1 ]
Gnegy, Chet N. [2 ]
Shibata, Tadashi [3 ]
Dash, Denver [4 ]
Chiarulli, Donald M. [1 ,5 ]
Levitan, Steven P. [1 ]
机构
[1] Univ Pittsburgh, Dept Elect & Comp Engn, Pittsburgh, PA 15260 USA
[2] Stanford Univ, Ctr Comp Res Mus & Acoust, Stanford, CA 94305 USA
[3] Univ Tokyo, Chiba 2778561, Japan
[4] Magic Leap, Dania, FL 33004 USA
[5] Univ Pittsburgh, Dept Comp Sci, Pittsburgh, PA 15260 USA
来源
IEEE JOURNAL ON EXPLORATORY SOLID-STATE COMPUTATIONAL DEVICES AND CIRCUITS | 2015年 / 1卷
基金
美国国家科学基金会;
关键词
Associative processing; emerging technology; image recognition; nearest neighbor search; non-Boolean functions; oscillator-based computing;
D O I
10.1109/JXCDC.2015.2507863
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We present the design and the performance of a hierarchical associative memory (AM) based on phase locking of coupled oscillators used for pattern recognition. The use of coupled oscillators, rather than Boolean logic, provides for implementations using emerging nanotechnology, such as magnetic spin-torque oscillators and resonant body transistor oscillators, which have the potential of lower energy and higher density than CMOS solutions. We develop a model for the general behavior of weakly coupled nonlinear oscillators that perform pattern matching using a simulation of coupled CMOS ring oscillators. We derive a simple analytic model for their phase locking behavior and use this reduced model in a hierarchical AM for image recognition tasks, such as identifying handwritten numbers.
引用
收藏
页码:94 / 102
页数:9
相关论文
共 28 条
[1]  
Asai T., 2004, INT J UNCONV COMPUT, V1, P123
[2]   Boolean logic and alternative information - Processing devices [J].
Bourianoff, George ;
Brewer, Joe E. ;
Cavin, Ralph ;
Hutchby, James A. ;
Zhirnov, Victor .
COMPUTER, 2008, 41 (05) :38-+
[3]   Nanoelectronics Research for Beyond CMOS Information Processing [J].
Bourianoff, George ;
Brillouet, Michel ;
Cavin, Ralph K., III ;
Hiramoto, Toshiro ;
Hutchby, James A. ;
Ionescu, Adrian M. ;
Uchida, Ken .
PROCEEDINGS OF THE IEEE, 2010, 98 (12) :1986-1992
[4]  
Cheriton D. R., 2006, U. S. Patent, Patent No. [7 051 078 B1, 7051078]
[5]   Training invariant support vector machines [J].
Decoste, D ;
Schölkopf, B .
MACHINE LEARNING, 2002, 46 (1-3) :161-190
[6]   Injection-Locked Spin Hall-Induced Coupled-Oscillators for Energy Efficient Associative Computing [J].
Fan, Deliang ;
Maji, Supriyo ;
Yogendra, Karthik ;
Sharad, Mrigank ;
Roy, Kaushik .
IEEE TRANSACTIONS ON NANOTECHNOLOGY, 2015, 14 (06) :1083-1093
[7]  
Fang Y, 2015, EMERGING NANOELECTRONIC DEVICES, P467
[8]  
Fang Y, 2014, ICCAD-IEEE ACM INT, P86, DOI 10.1109/ICCAD.2014.7001336
[9]  
Foster C., 1976, CONTENT ADDRESSABLE
[10]   A fast learning algorithm for deep belief nets [J].
Hinton, Geoffrey E. ;
Osindero, Simon ;
Teh, Yee-Whye .
NEURAL COMPUTATION, 2006, 18 (07) :1527-1554