Evolutionary Developmental Biology Can Serve as the Conceptual Foundation for a New Design Paradigm in Artificial Intelligence

2025-06-15

AI Summary

Contemporary AI research lacks a unifying theoretical framework; mainstream neural network paradigms suffer from fundamental limitations—including loosely organized architectures and uncontrollable learning dynamics—and have long neglected insights from evolutionary developmental biology (EDB). Method: This paper establishes, for the first time, a systematic deep analogy between the Modern Synthesis of evolution and machine learning, translating core EDB principles—such as regulatory connectivity, somatic variation-and-selection, and weak coupling—into computationally tractable AI design principles. It proposes a developmentally inspired modeling paradigm integrating regulatory network modeling, variation-and-selection learning, and modular decoupled architecture. Contribution/Results: Two biologically grounded learning systems are designed, jointly mitigating overfitting, catastrophic forgetting, and generalization bottlenecks, while reciprocally advancing theoretical understanding of evolutionary mechanisms.

Technology Category

• Machine Learning: Evolutionary Learning
• Cognitive Modeling & Cognitive Systems: Analogy
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Artificial intelligence (AI), propelled by advancements in machine learning, has made significant strides in solving complex tasks. However, the current neural network-based paradigm, while effective, is heavily constrained by inherent limitations, primarily a lack of structural organization and a progression of learning that displays undesirable properties. As AI research progresses without a unifying framework, it either tries to patch weaknesses heuristically or draws loosely from biological mechanisms without strong theoretical foundations. Meanwhile, the recent paradigm shift in evolutionary understanding -- driven primarily by evolutionary developmental biology (EDB) -- has been largely overlooked in AI literature, despite a striking analogy between the Modern Synthesis and contemporary machine learning, evident in their shared assumptions, approaches, and limitations upon careful analysis. Consequently, the principles of adaptation from EDB that reshaped our understanding of the evolutionary process can also form the foundation of a unifying conceptual framework for the next design philosophy in AI, going beyond mere inspiration and grounded firmly in biology's first principles. This article provides a detailed overview of the analogy between the Modern Synthesis and modern machine learning, and outlines the core principles of a new AI design paradigm based on insights from EDB. To exemplify our analysis, we also present two learning system designs grounded in specific developmental principles -- regulatory connections, somatic variation and selection, and weak linkage -- that resolve multiple major limitations of contemporary machine learning in an organic manner, while also providing deeper insights into the role of these mechanisms in biological evolution.

Problem

• Current AI lacks structural organization and progressive learning.
• AI research needs a unifying framework grounded in biology.
• Evolutionary Developmental Biology can address AI's major limitations.

Innovation

• Evolutionary Developmental Biology as AI foundation
• Regulatory connections resolve learning limitations
• Somatic variation and selection enhance AI