Publication
Hardware implementation of a bio-plausible neuron model for evolution and growth of spiking neural networks on FPGA
AbstractThe natural-language approach to identifying biological analogies exploits the existing format of much biological knowledge, beyond databases created for biomimetic design. However, designers may need to select analogies from search results, during which biases may exist toward: specific words in descriptions of biological phenomena, familiar organisms and scales, and strategies that match preconceived solutions. Therefore, we conducted two experiments to study the effect of abstraction on overcoming these biases and selecting biological phenomena based on analogical similarities.
Download publicationAssociated Researchers
Related Resources
See what’s new.
2024
Toward Automated Programming for Robotic Assembly Using ChatGPTBy using specialized language agents for task decomposition and code…
2024
From Keynotes to Art Installations: Autodesk Research Sizzled at AU 24Check out how Autodesk Research made a splash at AU 2024 …
2024
FluidsFormer: A Transformer-Based Approach for Continuous Fluid InterpolationGiven input keyframes, our approach interpolates substeps of a fluid…
2023
Multi-split configuration design for fluid-based thermal management systemsThis work introduces a framework for automated exploration of optimal…
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