Toward Human-Level Artificial Intelligence

TL;DR

This paper proposes a comprehensive framework for developing human-level AI, including a new definition, a simulated environment for testing, and a cognitive architecture inspired by the neocortex and brain structures.

Contribution

It introduces a novel definition of HLAI based on learning from language, a simulated environment called SEDRo, and a cognitive architecture named mHPM that models brain functions.

Findings

Developed the SEDRo environment simulating human baby experiences.

Proposed the mHPM architecture inspired by neocortical and brain structures.

Outlined a new definition of HLAI centered on language-based learning.

Abstract

In this paper, we present our research on programming human-level artificial intelligence (HLAI), including 1) a definition of HLAI, 2) an environment to develop and test HLAI, and 3) a cognitive architecture for HLAI. The term AI is used in a broad meaning, and HLAI is not clearly defined. I claim that the essence of Human-Level Intelligence to be the capability to learn from others' experiences via language. The key is that the event described by language has the same effect as if the agent experiences it firsthand for the update of the behavior policy. To develop and test models with such a capability, we are developing a simulated environment called SEDRo. There is a 3D Home, and a mother character takes care of the baby (the learning agent) and teaches languages. The environment provides comparable experiences to that of a human baby from birth to one year. Finally, I propose a cognitive architecture of HLAI called Modulated Heterarchical Prediction Memory (mHPM). In mHPM, there are three components: a universal module that learns to predict the next vector given the sequence of vector signals, a heterarchical network of those modules, and a reward-based modulation of learning. mHPM models the workings of the neocortex but the innate auxiliary units such hippocampus, reward system, instincts, and amygdala play critical roles, too.