Publication
A Multi-cellular Developmental Representation for Evolution of Adaptive Spiking Neural Microcircuits in an FPGA
Abstract
It has been shown that evolutionary and developmental processes can be used for emergence of scalability, robustness and fault-tolerance in hardware. However, designing a suitable representation for such processes is far from straightforward. Here, a bio-inspired developmental genotype-phenotype mapping for evolution of spiking neural microcircuits in an FPGA is introduced, based on a digital neuron model and cortex structure suggested and verified previously by the authors. The new developmental process is based on complex multi-cellular protein-protein and gene-protein interactions and signaling. Suitability of the representation for evolution of useful architectures and its adaptability is shown through statistical analysis and examples of scalability, modularity and fault-tolerance.
Download publicationAssociated Researchers
Related Resources
See what’s new.
2018
Leveraging Community-Generated Videos and Command Logs to Classify and Recommend Software Workflows
Users of complex software applications often rely on inefficient or…
2013
Design Tools for the Rest of Us: Maker Hardware Requires Maker Software
In our own work, we are developing and applying a system which…
2017
A Taxonomy of Event Time Representations
Terms such as “simulated time,” “simulation time,” “virtual time,”…
2012
CMC surfaces condensing to geodesic rays and segments in Riemannian manifolds
We construct examples of compact and one-ended constant mean curvature…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us