NeuroGenesys.
Research Desk • Category

Continual Learning

2 articles on continual learning from the NeuroGenesys Research Desk, newest first. Every claim is linked to its source.

  1. A single amber beam rising from a wide disc of white light on a wet salt flat at night, with small violet lanterns scattered dimly around it
    • 5 min read

    A better router helps, but on CIFAR-100 the experts were the weak link

    We pre-registered six predictions about how to route inputs among frozen experts and tested them on 30 cached expert libraries. A router in a shared feature space beat the experts' own confidence, by a little without pretraining and by a lot with it. But once routing was good, a plain readout of the shared features beat the experts themselves by 13 points.

  2. A violet lantern and an amber lantern standing side by side on a wet salt flat at night, under a thin, steady arc of pale light along the horizon
    • 6 min read

    A new model generation should earn authority, not win a contest

    When new models or new knowledge replace old ones, the usual picture is competition: old and new fight, the winner takes over. Our synthesis argues for graded succession instead. The successor gains authority step by step as independent evidence shows it is better, the old generation stays recoverable, and a protected constitution changes only by explicit amendment.

Leadership

A word from the founder — on why the brain is the blueprint, and why the next decade of intelligence will be built here.

"The brain is the universe's only proof that general intelligence is possible. We treat it as the blueprint."

From cortical interfaces to photonic silicon, every program at NeuroGenesys exists to answer one question: how does intelligence arise — and how do we build it safely.

Will Schulz

Will Schulz

Founder, NeuroGenesys • AW3 Technology