Publication
An FPGA-based model suitable for evolution and development of spiking neural networks
AbstractWe propose a digital neuron model suitable for evolving and growing heterogeneous spiking neural networks on FPGAs using a piecewise linear approximation of the Quadratic Integrate and Fire (QIF) model. A network of 161 neurons and 1610 synapses with 4210 times realtime neuron simulation speed was simulated and synthesized for a Virtex-5 chip.
Download publicationAssociated Researchers
Related Resources
See what’s new.
2024
Autodesk at SIGGRAPH 2024: Bridging the Gap Between AI and CreativityLearn how Autodesk Research is exploring the latest trends in AI in…
2024
Generative Design through Quality-Diversity Data Synthesis and Language ModelsA new paradigm for AEC design exploration, based on a combination of…
2015
NanoStylus: Enhancing Input on Ultra-Small Displays with a Finger-Mounted StylusDue to their limited input area, ultra-small devices, such as…
2014
Effects of Abstraction on Selecting Relevant Biological Phenomena for Biomimetic DesignThe natural-language approach to identifying biological analogies…
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