Subjectivity Learning Theory towards Artificial General Intelligence

TL;DR

This paper introduces subjectivity learning theory, a novel approach that breaks traditional data constraints to advance towards artificial general intelligence by modeling data with a philosophical concept of subjectivity.

Contribution

It develops a new learning framework that overcomes key assumptions of traditional machine learning, providing theoretical foundations for AGI development.

Findings

Subjectivity learning has a lower risk bound than traditional methods.

The theory establishes conditions for consistency in learning.

Proposes empirical global risk minimization as a practical learning process.

Abstract

The construction of artificial general intelligence (AGI) was a long-term goal of AI research aiming to deal with the complex data in the real world and make reasonable judgments in various cases like a human. However, the current AI creations, referred to as "Narrow AI", are limited to a specific problem. The constraints come from two basic assumptions of data, which are independent and identical distributed samples and single-valued mapping between inputs and outputs. We completely break these constraints and develop the subjectivity learning theory for general intelligence. We assign the mathematical meaning for the philosophical concept of subjectivity and build the data representation of general intelligence. Under the subjectivity representation, then the global risk is constructed as the new learning goal. We prove that subjectivity learning holds a lower risk bound than traditional machine learning. Moreover, we propose the principle of empirical global risk minimization (EGRM) as the subjectivity learning process in practice, establish the condition of consistency, and present triple variables for controlling the total risk bound. The subjectivity learning is a novel learning theory for unconstrained real data and provides a path to develop AGI.