Dynamic Neural Fields with Lava
-
Updated
May 13, 2026 - Jupyter Notebook
Dynamic Neural Fields with Lava
A C++20 library and interactive application for building and simulating Dynamic Neural Field (DNF) architectures.
dynamic-neural-field-degeneration is a framework designed to simulate and study the effects of artificial neural degeneration on Dynamic Neural Field (DNF) models. This work explores the resilience and adaptability of DNFs, specifically in the context of cognitive behavior in robotic systems.
Neuroevolution of Dynamic Neural Field control architectures for adaptive Human–Robot Collaboration.
This project explores anticipatory robot behavior in human-robot collaboration using dynamic neural fields. Through virtual reality experiments, we demonstrate that robots capable of anticipating human intentions create smoother interactions, fewer collisions, and improved user satisfaction.
A C++ library that combines NEAT (NeuroEvolution of Augmenting Topologies) with Dynamic Neural Fields (DNFs) to automatically evolve interpretable, neurally inspired control architectures.
Benchmarking and cross-platform validation suite for four Dynamic Field Theory implementations — Cedar (C++), Cosivina (MATLAB), Cosivina (Python), and dnf-composer (C++) — measuring simulation throughput and verifying algebraic equivalence across 100 neural field scenarios.
Add a description, image, and links to the dynamic-neural-fields topic page so that developers can more easily learn about it.
To associate your repository with the dynamic-neural-fields topic, visit your repo's landing page and select "manage topics."