Danyal Akarca
2 papers · Latest:
Neural & Evolutionary Computing
Unifying Dynamical Systems and Graph Theory to Mechanistically Understand Computation in Neural Networks
Unifying dynamical systems and graph theory, this paper shows neural network computation relies on multi-hop pathways, introducing R-RNNs for improved temporal sparsity.
2605.03598
Neural & Evolutionary ComputingThe Principle of Maximum Heterogeneity Optimises Productivity in Distributed Production Systems Across Biology, Economics, and Computing
This paper introduces the Principle of Maximum Heterogeneity, showing how diverse configurations optimize productivity across biological, economic, and computational systems.
2604.07602
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.