Modularity is the Bedrock of Natural and Artificial Intelligence

Alessandro Salatiello

Track: long paper (up to 10 pages)

Domain: machine learning

Abstract:

The astonishing performance showcased by AI systems in the last decade has been achieved through the use of massive amounts of data, computation, and, in turn, energy, which vastly exceed what human intelligence requires. This wide gap underscores the need for further research and points to leveraging brains as a valuable source of guiding principles.
On the other hand, the No Free Lunch Theorem highlights that effective inductive biases must be problem-specific. This suggests designing architectures with specialized components that can solve subproblems --- namely, modular architectures.
Interestingly, modularity is an established principle of brain organization that is considered essential for supporting the efficient learning and strong generalization abilities consistently demonstrated by humans.
However, despite its importance in natural intelligence and the proven benefits it has shown across various seemingly unrelated AI research areas, modularity remains underappreciated in AI.
Thus, here we argue for the need to place modularity principles center stage when designing AI systems, as modularity forms the bedrock of both natural and artificial intelligence.
In particular, we will examine what computational advantages modularity provides, how it has emerged as a solution in several AI research areas, which modularity principles the brain exploits, and how modularity can help bridge the gap between natural and artificial intelligence.

Submission Number: 28