Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution

TL;DR

This paper advocates for integrating neuroscience insights into AI development through the embodied Turing test, aiming to create models that emulate animal sensorimotor skills and accelerate AI progress.

Contribution

It introduces the embodied Turing test as a new benchmark for AI, emphasizing evolutionary shared capabilities and fostering fundamental NeuroAI research.

Findings

Proposes the embodied Turing test as a new AI benchmark

Highlights the importance of sensorimotor skills inherited from evolution

Suggests this approach will guide next-generation AI development

Abstract

Neuroscience has long been an essential driver of progress in artificial intelligence (AI). We propose that to accelerate progress in AI, we must invest in fundamental research in NeuroAI. A core component of this is the embodied Turing test, which challenges AI animal models to interact with the sensorimotor world at skill levels akin to their living counterparts. The embodied Turing test shifts the focus from those capabilities like game playing and language that are especially well-developed or uniquely human to those capabilities, inherited from over 500 million years of evolution, that are shared with all animals. Building models that can pass the embodied Turing test will provide a roadmap for the next generation of AI.