🚀NEW LABGetting Started with Claude AgentsStart lab
Architecture

Neural Developmental Programs (NDPs)

First page
Neural Developmental Programs (NDPs)
Paper summary

Proposes neural networks that self-assemble through a developmental process inspired by biological embryonic development.

Ask this paper

Key points
01

Bio-inspired growth: A small set of developmental rules governs how neurons replicate and connect, mirroring the way biological nervous systems grow from genomes.

02

Indirect encoding: The final network emerges from a much smaller developmental program rather than being specified directly - an indirect encoding scheme.

03

Self-assembly: Networks self-assemble through repeated application of local developmental rules, without a global blueprint.

04

Research direction: Positioned as a step toward more open-ended, flexible neural architectures that could eventually grow and adapt throughout training rather than being fixed a priori.

Every Monday
Get next week’s papers.
Subscribe on Substack