Title :
Neuroscience-inspired inspired dynamic architectures
Author :
Schuman, Catherine D. ; Birdwell, J. Douglas ; Dean, Mark
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Univ. of Tennessee Knoxville, Knoxville, TN, USA
Abstract :
Neuroscience-inspired computational elements and architectures are one of the most popular ideas for replacing the von Neumann architecture. In this work, we propose a neuroscience-inspired dynamic architecture (NIDA) and discuss a method for automatically designing NIDA networks to accomplish tasks. We discuss the reasons we chose evolutionary optimization as the main design method and propose future directions for the work.
Keywords :
evolutionary computation; medical computing; neurophysiology; automatically designing NIDA networks; evolutionary optimization; main design method; neuroscience-inspired computational elements; neuroscience-inspired dynamic architectures; Biological neural networks; Computer architecture; Delays; Design methodology; Neurons; Optimization;
Conference_Titel :
Biomedical Science and Engineering Center Conference (BSEC), 2014 Annual Oak Ridge National Laboratory
Conference_Location :
Oak Ridge, TN
DOI :
10.1109/BSEC.2014.6867735
