Danko Nikolic

Danko Nikolic

Frankfurt Rhine-Main Metropolitan Area
13K followers 500+ connections

About

As the Head of AI and Data Science, I lead a team of experts in developing and delivering…

Articles by Danko

See all articles

Activity

Join now to see all activity

Experience

  • Robots Go Mental Graphic

    Robots Go Mental

    Frankfurt am Main Area, Germany

  • -

  • -

  • -

    Frankfurt am main

  • -

  • -

  • -

    Frankfurt am Main, Hesse

  • -

    Frankfurt Am Main Area, Germany

  • -

    Zagreb, Croatia

  • -

    Frankfurt am Main und Umgebung, Deutschland

  • -

  • -

  • -

    Wiesbaden Area, Germany

  • -

  • -

    Darmstadt, Hesse, Germany

Education

Publications

  • Why deep neural nets cannot ever match biological intelligence and what to do about it?

    International Journal of Automation and Computing

    Explains why we need AI founded in the theory of practopoiesis.

    See publication
  • Practopoiesis: Or how life fosters a mind

    Journal of Theoretical Biology

    This is my theory on how life is functionally organized and how then a mind emerges out of that organization.

    See publication
  • Distributed Fading Memory for Stimulus Properties in the Primary Visual Cortex

    PLoS Biology

    My pioneering work on "mind reading" using machine learning to interpret neural activity.

    Other authors
    See publication
  • Temporal dynamics of information content carried by neurons in the primary visual cortex.

    Advances in Neural Information Processing Systems (NIPS)

    We use multi-electrode recordings from cat primary visual cortex and investigate
    whether a simple linear classier can extract information about the presented stimuli.
    We found that information was extractable and that it lasted for several hundreds
    milliseconds after the stimulus has been removed. In a fast sequence of stimulus
    presentation, information about both new and old stimuli is present simultaneously
    and nonlinear relations between these stimuli can be extracted…

    We use multi-electrode recordings from cat primary visual cortex and investigate
    whether a simple linear classier can extract information about the presented stimuli.
    We found that information was extractable and that it lasted for several hundreds
    milliseconds after the stimulus has been removed. In a fast sequence of stimulus
    presentation, information about both new and old stimuli is present simultaneously
    and nonlinear relations between these stimuli can be extracted. These
    results suggest nonlinear properties of cortical representations. The important implications
    of these properties for the nonlinear brain theory are discussed.

    See publication

Patents

  • AI-Kindergarten: A method for developing biological-like artificial intelligence. (provisional)

    Filed US

Languages

  • Croatian

    Native or bilingual proficiency

  • English

    Full professional proficiency

  • German

    Professional working proficiency

Organizations

  • Max Planck Society

    Group Leader

    -

Recommendations received

More activity by Danko

View Danko’s full profile

  • See who you know in common
  • Get introduced
  • Contact Danko directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Danko Nikolic

Add new skills with these courses