Stories
Slash Boxes
Comments

SoylentNews is people

posted by janrinok on Tuesday November 15 2022, @08:34AM   Printer-friendly
from the great-for-identifying-cheeses dept.

Researchers for the Human Brain Project have trained a large-scale computer model of the mouse primary visual cortex to accurately solve five visual tasks.

[A] study by Human Brain Project (HBP) researchers from the Graz University of Technology (Austria) showed how a large data-based model can reproduce a number of the brain's visual processing capabilities in a versatile and accurate way. The results were published in the journal Science Advances.

With the help of the PCP Pilot Systems at the Jülich Supercomputing Centre, developed in a collaboration between the HBP and the software company Nvidia, the team analysed a biologically detailed large-scale model of the mouse primary visual cortex that can solve multiple visual processing tasks. This model provides the largest integration of anatomical detail and neurophysiological data currently available for the visual cortex area V1, which is the first cortical region to receive and process visual information.

The model is built with a different architecture than those of deep neural networks used in current AI, and the researchers found out that it has interesting advantages regarding learning speed and visual processing performance over models that are commonly used for visual processing in AI.

The model was able to solve all five visual tasks presented by the team with high accuracy. For instance, these tasks involved classifying images of hand-written numbers or detecting visual changes in a long sequence of images. Strikingly, the virtual model achieved the same high performance as the brain even when the researchers subjected the model to noise in the images and in the network that it had not encountered during training.

Original Publication: Chen Guozhang, Franz Scherr & Wolfgang Maass (2022). A data-based large-scale model for primary visual cortex enables brain-like robust and versatile visual processing. Science Advances, DOI: 10.1126/sciadv.abq7592


Original Submission

This discussion was created by janrinok (52) for logged-in users only, but now has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
(1)
  • (Score: 2, Funny) by Anonymous Coward on Tuesday November 15 2022, @05:02PM (1 child)

    by Anonymous Coward on Tuesday November 15 2022, @05:02PM (#1279882)

    Next we'll have mouse-models driving cars. Maybe that's better than computers driving cars?

    • (Score: 3, Funny) by acid andy on Tuesday November 15 2022, @05:59PM

      by acid andy (1683) on Tuesday November 15 2022, @05:59PM (#1279889) Homepage Journal

      Well the concept of one mouse driving a car is preposterous: they quite obviously lack the brain power to tackle such a complex series of tasks. On the other hand, an army of many hundreds of mice, each meticulously trained to perform exactly one function--much in the spirit of UNIX design--would, I imagine, work wonderfully well. PATENT PENDING!

      --
      If a cat has kittens, does a rat have rittens, a bat bittens and a mat mittens?
(1)