7 comments

  • rini17 3 days ago

    I guess it's impossible to simulate billions of dynamical neurons with current computer architecture, it is limited by memory bandwidth.

    • tonii141 3 days ago

      I agree, but maybe there is no need for billions of neurons to be simulated right away. Artificial neural networks were pretty small at the time.

      • rini17 2 days ago

        and they did not do much

        • tonii141 2 days ago

          Not true. AI has been around far longer than modern LLMs and has performed well in non-generative areas, often with orders of magnitude fewer parameters.

  • nialse 3 days ago

    Dynamical neurons are not used because they add enormous computational cost and instability for limited practical gain.

    • tonii141 3 days ago

      What do you mean by "they add instability"?

      • nialse 2 days ago

        Neural nets are unstable during training and dynamic weights amplifies the problem. Thus, the neural networks could end up in totally unusable states at inference time.