Vision System for AGI: Problems and Directions

TL;DR

This paper explores the necessary frameworks and architectures for creating an AGI vision system, proposing a formal perception model and analyzing the roles of discriminative and generative models, along with architectural challenges.

Contribution

It introduces a formal perception model for AGI vision systems and evaluates the limitations of existing models, highlighting architectural dilemmas and open research questions.

Findings

Discriminative and generative models are crucial for AGI perception.

Existing models are insufficient for the requirements of AGI vision.

Open questions remain regarding optimal architectural design.

Abstract

What frameworks and architectures are necessary to create a vision system for AGI? In this paper, we propose a formal model that states the task of perception within AGI. We show the role of discriminative and generative models in achieving efficient and general solution of this task, thus specifying the task in more detail. We discuss some existing generative and discriminative models and demonstrate their insufficiency for our purposes. Finally, we discuss some architectural dilemmas and open questions.