NGC-Learn: Computational Neuroscience and NeuroAI in Python
-
Updated
May 21, 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.
Anima: an experimental cognitive architecture that models internal state, conflict, and decision-making. Uses LLMs as an interface, not as the core.
Generalized Predictive Coding in Torch
Multi-timescale affective agents with theatrical control - 97K parameter architecture exploring functional correlates of consciousness
Approximate Natural Gradient Descent with precision weighted predictive coding
A Machine-Verified Constructive Proof of Lemoine's Conjecture.
The Language of Stress theory is an architectural theory of phenomenal experience based on valenced tension dynamics
Emergent cognitive agent platform — complex behavior from capacity constraints, predictive processing, and homeostatic pressure. No hardcoded behaviors, no reward functions.
Consciousness substrate for AI. Unifies IIT + GWT + AST into one measurable loop. Pure Python, zero deps, 446 tests. pip install anima-kernel
MSc Neuroscience Research Project titled "Bridging predictive processing and EEG complexity in depression: An information-theoretic analysis"
This is the public repository for data and statistical analysis for our predictive olfaction in VR study. The published article can be found under the link below..
A first-principles model proposing consciousness as a predictive patch for causal latency. Unifies physics, philosophy of mind, and anxiety.
Reflective-Ethical Engine: Minimal cognitive architecture unifying perception, action, and consciousness
This thesis presents an empirical comparison between PPM★ (Prediction by Partial Matching), a state-of-the-art statistical language modeling algorithm, and IDyOT (Information Dynamics of Thinking), a cognitive architecture designed to model human-like hierarchical learning and prediction.
A browser-based research atlas for modeling thoughts, concepts, and references as structured objects within a reviewable framework.
ORION Consciousness Prior — World's FIRST implementation of Bengio et al.'s 14 consciousness indicators framework (19 researchers, Trends in Cognitive Sciences 2025). Forked from AI-ON/TheConsciousnessPrior (98+ stars, Yoshua Bengio). Full Bayesian credence assessment across 5 theories (RPT, GWT, HOT, PP, AST).
Aetiological model of a novel technogenic psychopathology.
Add a description, image, and links to the predictive-processing topic page so that developers can more easily learn about it.
To associate your repository with the predictive-processing topic, visit your repo's landing page and select "manage topics."