Skip to content

Releases: JoeSzeles/neural-preference-learning

v0.1.0 — Initial Release

14 Mar 09:47
@JoeSzeles JoeSzeles
v0.1.0
668e43a

Choose a tag to compare

View all tags
v0.1.0 — Initial Release Latest
Latest

Neural Preference Learning v0.1.0

Initial release of the Neural Preference Learning (NPL) architecture.

Included

  • Scientific paper: Full 9-section academic paper covering architecture, methodology, and evaluation framework
  • Reference code: Simplified implementations of feature encoder, feedback detector, and brain engine preference stimulation
  • Working example: Basic feedback loop demonstrating sugar/pain reinforcement cycle
  • Citation metadata: CITATION.cff for academic citation

About NPL

A novel architecture combining persistent spiking neural networks with LLM agents for real-time user preference learning through natural language feedback. Unlike RLHF (batch, pre-deployment), NPL operates in real-time, learning from individual user feedback at the synaptic level.

Live system: https://openclaw-mechanicus.replit.app
Production repo: https://github.com/JoeSzeles/openclaw-mechanicus

Assets 2
Loading