Neural DNA: A Compact Genome for Growing Network Architecture

Read full text Summarise with VIRAT
Authors: Tejas Parthasarathi Sudarshan
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

We introduce Neural DNA (NDNA), a compact learned genome of fewer than 300 parameters that grows neural network topology through type-based compatibility rules, default-disconnected initialization, and metabolic cost pressure. NDNA consistently outperforms random sparsity by 0.39% to 7.01% across three architectures (MLP, CNN, Transformer) and five datasets (MNIST, CIFAR-10, CIFAR-100, Fashion-MNIST, IMDB). Topology transfers across tasks without modification. Compression ratios scale with network size, reaching 8,384:1 on the largest architecture tested.

Fields of Study & Subjects

Evolutionary Algorithms and Applications Advanced Neural Network Applications Neural Networks and Applications

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
26 March 2026
Language
EN
Document type
Preprint