Live
- 76th NCC Day celebrated with enthusiasm at GITAM
- Atishi accuses Centre of exploiting electoral rolls
- Collector inaugurates digital library in Rajendranagar
- Visakhapatnam: ACB conducts searches at residence, office
- Hyderabad Swimming Championship concludes on a high
- City cops begin drive to clear encroachments on footpaths
- 14th IconSWM-CE & IPLA GF 2024 from November 28
- Paisa Vasool! Beggars rule the roost at traffic signals
- Vizianagaram: Roads to get facelift by Sankranti
- CM directs Collectors to expedite paddy procurement
Just In
Humans can categorise data using less than one per cent of the original information, say scientists, including those of Indian-origin, who have found an algorithm to explain human learning. The method can also be used for machine learning, data analysis and computer vision, researchers said.
The researchers created three families of abstract images at 150x150 pixels, then very small 'random sketches' of those images. Test subjects were shown the whole image for 10 seconds, then randomly shown 16 sketches of each. Using abstract images ensured that neither humans nor machines had any prior knowledge of what the objects were. "We were surprised by how close the performance was between extremely simple neural networks and humans," Vempala said. "This fascinating paper introduces a localised random projection that compresses images while still making it possible for humans and machines to distinguish broad categories," said Sanjoy Dasgupta, professor at the University of California San Diego. The study was published in the journal Neural Computation.
© 2024 Hyderabad Media House Limited/The Hans India. All rights reserved. Powered by hocalwire.com