On Sat, Aug 28, 2021 at 4:22 AM Ben Goertzel <b...@goertzel.org> wrote:
> Matt, "Quantum Associative Memory" is an active research area... > > So are reversible NNs, e.g. https://arxiv.org/abs/2108.05862 > > I think your current view that "learning means writing bits into > memory." is overly limited... And that's just a memory model? There is also Bob Coecke's group around Oxford who are looking at quantum perspectives which change the conceptualization of the intelligence problem from the current one of "learning" parameters, entirely, to something he contrasts as "togetherness". So more active, dynamic, something which embraces contradictions inherently within itself, e.g: >From quantum foundations via natural language meaning to a theory of everything Bob Coecke https://arxiv.org/abs/1602.07618 So moving right away from the idea of intelligence as some kind of "learned" weight adjustment system, in the first place. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf6dddebe1e89183a-M6b44cf935242b95cd7a2270b Delivery options: https://agi.topicbox.com/groups/agi/subscription
