Control tasks involving dramatic non-linearities, such as decision making, can be challenging for classical design methods. However, autonomous stochastic design methods have proved effective. In particular, Genetic Algorithms (GA) that create phenotypes by the application of genotypes comprising rules are robust and highly scalable. Such encodings are useful for complex applications such as artificial neural net design. This paper outlines an evolutionary algorithm that creates C++ programs which in turn create Artificial Neural Networks (ANNs) that can functionally perform as an exclusive-OR logic gate. Furthermore, the GAs are able to create scalable ANNs robust enough to feature redundancies that allow the network to function despite internal failures.
- Design Engineering Division and Computers in Engineering Division
Genetic Evolution for the Development of Robust Artificial Neural Network Logic Gates
- Views Icon Views
- Share Icon Share
- Search Site
Roy, AM, Antonsson, EK, & Shapiro, AA. "Genetic Evolution for the Development of Robust Artificial Neural Network Logic Gates." Proceedings of the ASME 2009 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. Volume 5: 35th Design Automation Conference, Parts A and B. San Diego, California, USA. August 30–September 2, 2009. pp. 123-130. ASME. https://doi.org/10.1115/DETC2009-87448
Download citation file: