An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures

Conference · Fri Jan 01 00:00:00 EST 2016

DOI:https://doi.org/10.1109/IJCNN.2016.7727192· OSTI ID:1332072

Schuman, Catherine D ^[1]; Plank, James ^[2]; Disney, Adam ^[2]; Reynolds, John ^[2]

---

1. ORNL
2. University of Tennessee (UT)

As new neural network and neuromorphic architectures are being developed, new training methods that operate within the constraints of the new architectures are required. Evolutionary optimization (EO) is a convenient training method for new architectures. In this work, we review a spiking neural network architecture and a neuromorphic architecture, and we describe an EO training framework for these architectures. We present the results of this training framework on four classification data sets and compare those results to other neural network and neuromorphic implementations. We also discuss how this EO framework may be extended to other architectures.

• Research Organization: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE Laboratory Directed Research and Development (LDRD) Program
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1332072
• Resource Relation: Conference: World Congress on Computational Intelligence 2016 - International Joint Conference on Neural Networks, Vancouver, Canada, 20160724, 20160729
• Country of Publication: United States
• Language: English