Modularity is the Bedrock of Natural and Artificial Intelligence
Preprint
Abstract
The remarkable performance of modern AI systems has been driven by unprecedented scales of data, computation, and energy -- far exceeding the resources required by human intelligence. This disparity highlights the need for new guiding principles and motivates drawing inspiration from the fundamental organizational principles of brain computation. Among these principles, modularity has been shown to be critical for supporting the efficient learning and strong generalization abilities consistently exhibited by humans. Furthermore, modularity aligns well with the No Free Lunch Theorem, which highlights the need for problem-specific inductive biases and motivates architectures composed of specialized components that solve subproblems. However, despite its fundamental role in natural intelligence and its demonstrated benefits across a range of seemingly disparate AI subfields, modularity remains relatively underappreciated in mainstream AI research. In this work, we review several research threads in artificial intelligence and neuroscience through a conceptual framework that highlights the central role of modularity in supporting both artificial and natural intelligence. In particular, we examine what computational advantages modularity provides, how it has emerged as a solution across several AI research areas, which modularity principles the brain exploits, and how modularity can help bridge the gap between natural and artificial intelligence.Keywords
All Related Versions
This publication has 64 references indexed in Scilit:
- Dissociating language and thought in large language modelsTrends in Cognitive Sciences, 2024
- Neurosymbolic AI: the 3rd waveArtificial Intelligence Review, 2023
- Single cortical neurons as deep artificial neural networksNeuron, 2021
- Embracing Change: Continual Learning in Deep Neural NetworksTrends in Cognitive Sciences, 2020
- How many words do we read per minute? A review and meta-analysis of reading rateJournal of Memory and Language, 2019
- Parcellating Cerebral Cortex: How Invasive Animal Studies Inform Noninvasive Mapmaking in HumansNeuron, 2018
- Modular representation of layered neural networksNeural Networks, 2018
- Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A reviewInternational Journal of Automation and Computing, 2017
- Connectionism and cognitive architecture: A critical analysisCognition, 1988
- Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectorsBiological Cybernetics, 1976