Backpropagation isn't just an algorithm; it's mathematically identical to how ant colonies evolve pheromone trails.
April 14, 2026
Original Paper
Isomorphic Functionalities between Ant Colony and Ensemble Learning: Part III -- Gradient Descent, Neural Plasticity, and the Emergence of Deep Intelligence
arXiv · 2604.09677
The Takeaway
This paper proves a formal isomorphism between SGD/neural plasticity and the generational learning of social insects. It suggests that the core mechanism of modern AI is a fundamental law of collective intelligence shared with the natural world.
From the abstract
In Parts I and II of this series, we established isomorphisms between ant colony decision-making and two major families of ensemble learning: random forests (parallel, variance reduction) and boosting (sequential, bias reduction). Here we complete the trilogy by demonstrating that the fundamental learning algorithm underlying deep neural networks -- stochastic gradient descent -- is mathematically isomorphic to the generational learning dynamics of ant colonies. We prove that pheromone evolution