Tag
Researchers at Delft University of Technology developed lightweight, cat-like whisker sensors that let tiny drones navigate by touch in darkness, smoke, or other vision-limited environments, with findings published in Nature Communications.
This paper proposes a bio-inspired deep learning framework for accurate odor mixture perception, achieving 92.2% accuracy and providing a generalizable solution to mixture perception challenges.
A tweet discusses an experiment where a fruit fly brain is used to tune an RTL-SDR FM radio, showcasing bio-inspired technology in radio applications.
The paper presents a biologically grounded framework where noisy neural and synaptic dynamics enable probabilistic inference and learning via stochastic sampling, using analogue in-memory computing hardware for scalable and energy-efficient computation.
Researchers have developed a bio-inspired algorithm called Spi-Fly, which mimics fruit fly olfactory systems using sparse coding to enable fast learning and prevent catastrophic forgetting in electronic noses.
Researchers at Penn Engineering and collaborators discovered that the skeleton of the sea star Protoreaster nodosus contains lens-like mineral structures that guide and concentrate light, suggesting nature can combine mechanical support and optical sensing in a single material system.
EvoSci proposes a bio-inspired multi-agent framework that integrates evolutionary algorithms with knowledge graph modeling to iteratively generate, evaluate, and refine research ideas, achieving top performance in peer-review evaluations.