A heterogeneous microprocessor for energy-scalable sensor inference using genetic programming

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@InProceedings{Jia:2017:VLSI,

• author = "Hongyang Jia and Jie Lu and Niraj K. Jha and Naveen Yerma",
• booktitle = "2017 Symposium on VLSI Circuits",
• title = "A heterogeneous microprocessor for energy-scalable sensor inference using genetic programming",
• year = "2017",
• pages = "C28--C29",
• abstract = "We present a heterogeneous microprocessor for IoE sensor-inference applications, which achieves programmability required for feature extraction strictly using application data. Acceleration, though key for energy efficiency, poses substantial programmability challenges. These are overcome by exploiting genetic programming (GP) for automatic program synthesis. GP yields highly structured models of computation, enabling: (1) high degree of specialization; (2) systematic mapping of programs to the accelerator; and (3) energy scalability via user-controllable approximation. The microprocessor (130nm) achieves 325times/156times energy reduction, and farther 20x/9x energy scalability, for programmable feature extraction in two medical-sensor applications (seizure/arrhythmia-detection) vs. GP-model execution on CPU. The energy efficiency is 220 GOPS/W, near that of fixed-function accelerators, exceeding typical programmable accelerators.",
• keywords = "genetic algorithms, genetic programming",
• DOI = "doi:10.23919/VLSIC.2017.8008535",
• month = jun,
• notes = "Also known as \cite{8008535}",

}

Genetic Programming entries for Hongyang Jia Jie (Lucy) Lu Niraj K Jha Naveen Yerma

Citations