Evolutionary Developmental Biology Can Serve as the Conceptual Foundation for a New Design Paradigm in Artificial Intelligence
2025/06/15 by Zeki Doruk Erden, Erden, Zeki Doruk, Boi Faltings +1
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial Intelligence (cs.AI) #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Genetics, Bioinformatics, and Biomedical Research #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.2506.12891
openalex publication_date 2025/06/15 · openalex created_date 2025/10/14 · openalex updated_date 2026/07/28
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.
Citations
- Foundations of a Developmental Design Paradigm for Integrated Continual Learning, Deliberative Behavior, and Comprehensibility
- Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models
- Neuro-Symbolic AI in 2024: A Systematic Review
- Directed Structural Adaptation to Overcome Statistical Conflicts and Enable Continual Learning
- The emerging view on the origin and early evolution of eukaryotic cells
- Evolved Developmental Artificial Neural Networks for Multitasking with Advanced Activity Dependence
- Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI
- FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time Series
- Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs
- A Survey of Large Language Models
- When, where, and how to add new neurons to ANNs
- Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments
- Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey
- Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey
- Connectionism, Complexity, and Living Systems: a comparison of Artificial and Biological Neural Networks
- Rethinking Experience Replay: a Bag of Tricks for Continual Learning
- Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
- Dark Experience for General Continual Learning: a Strong, Simple Baseline
- Multi-Task Reinforcement Learning with Soft Modularization
- A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
- Artificial intelligence for decision making in the era of Big Data – evolution, challenges and research agenda
- Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
- Sub-policy Adaptation for Hierarchical Reinforcement Learning
- Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural Networks
- AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
- Experience Replay for Continual Learning
- On the Power of Over-parametrization in Neural Networks with Quadratic Activation
- Deep Learning: A Critical Appraisal
- Learning to Compose Skills
- NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
- Enhancer evolution and the origins of morphological novelty
- Deep Reinforcement Learning: An Overview
- Modular Multitask Reinforcement Learning with Policy Sketches
- Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer
- Progressive Neural Networks
- The extended evolutionary synthesis: its structure, assumptions and predictions
- Adaptive evolution on neutral networks
- Alternative formulations of multilevel selection
- Punctuated equilibria: the tempo and mode of evolution reconsidered
Related