NGC-Learn: Computational Neuroscience and NeuroAI in Python
-
Updated
Sep 5, 2026 - Python
NGC-Learn: Computational Neuroscience and NeuroAI in Python
A computational theory of consciousness: if the universe is deterministic, consciousness is the observer function, not the executor. Tested across 4 AI substrates with 11 probes and 4 controls.
An honest, from-scratch, LLM-free instrument that implements the major scientific theories of consciousness (GWT · AST · HOT · active inference · IIT-proxy) as running code, a maximal functional attempt that never claims to be conscious.
Generalized Predictive Coding in Torch
Multi-timescale affective agents with theatrical control - 97K parameter architecture exploring functional correlates of consciousness
Two metrics for causal agency in artificial agents: directional ownership and expression congruence, with permutation baselines
Approximate Natural Gradient Descent with precision weighted predictive coding
Interactive visualization of Active Inference dynamics
Biologically-grounded reasoning agent, numpy-only, no LLM — Kisamapa Labs Experiment 06
A continuously running inner world for one AI persona — senses it can't author, a budget it can run out of, and guards that stop it when it stalls. Pairs with SoulScript Engine.
多代理人精度加權投資研究系統 — 以預測處理框架的 precision weighting 合成多個專家 Agent 的台股投資判斷,含走時序回測與校準評估
To associate your repository with the predictive-processing topic, visit your repo's landing page and select "manage topics."