Dynamic and Evolving Neural Network for Event Discrimination

EasyChair Preprint 7922, version 2

Abstract

Artificial general intelligence (AGI) should be founded on a suitable framework, e.g. a rule-based design or Deep Learning (DL). Here we choose the DL to be the basis for AGI.

An appropriate AGI is defined, followed by its appropriate DL implementation. We introduce an AGI, in the form of cognitive architecture, which is based on Global Workspace Theory (GWT). It consists of a supervisor, a working memory, specialized memory units, and processing units.
Additional discussion about the uniqueness of the visual and the auditory sensory channels is conducted.

Next, we introduce our DL module, which is dynamic, flexible, and evolving or growing. It can be also considered as a Network Architecture Search (NAS) method. It is a spatial-temporal model, with a hierarchy of both features and tasks, tasks such as objects or events.

Keyphrases: deep learning, dynamic, evolving, general intelligence

@booklet{EasyChair:7922,
  author    = {Shimon Komarovsky},
  title     = {Dynamic and Evolving Neural Network for Event Discrimination},
  howpublished = {EasyChair Preprint 7922},
  year      = {EasyChair, 2022}}