From Manifestations to Cognitive Architectures: a Scalable Framework
This work addresses the problem of developing scalable cognitive architectures for AGI, representing a new paradigm rather than an incremental improvement.
The paper tackles the challenge of advancing towards Artificial General Intelligence by proposing a novel framework that interprets reality as an information source and builds cognitive architectures like Long Term Memory and Working Memory from spatial distributed representations, achieving seamless scalability in a hierarchical manner.
The Artificial Intelligence field is flooded with optimisation methods. In this paper, we change the focus to developing modelling methods with the aim of getting us closer to Artificial General Intelligence. To do so, we propose a novel way to interpret reality as an information source, that is later translated into a computational framework able to capture and represent such information. This framework is able to build elements of classical cognitive architectures, like Long Term Memory and Working Memory, starting from a simple primitive that only processes Spatial Distributed Representations. Moreover, it achieves such level of verticality in a seamless scalable hierarchical way.