attractor-metadynamics-neural

Simulate neural attractor dynamics and plasticity with a Python framework.

2|Updated Feb 12, 2026

Search Tags:#neural-networks #dynamical-systems #continuous-learning #attractor #neural-dynamics #metadynamics #slow-adaptation

Ready to run

npx skills add https://github.com/hiyenwong/ai_collection --skill attractor-metadynamics-neural

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: attractor-metadynamics-neural
Source: https://github.com/hiyenwong/ai_collection/tree/main/collection/skills/attractor-metadynamics-neural
Command: npx skills add https://github.com/hiyenwong/ai_collection --skill attractor-metadynamics-neural

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

慢适应过程在神经网络的吸引子景观形成与演化中的作用不易把握。本技能提供一个元动力学框架，帮助研究者理解与模拟吸引子景观的动态塑形。

Core Features & Use Cases

能够通过慢适应调控吸引子景观的形成与演化的理论与实验框架
提供简单的 Python 实现用于仿真和可视化吸引子动态
支持连续学习场景中的长期记忆稳定性分析与评估

Quick Start

在默认参数下运行示例以观察吸引子景观的演化。

Frequently Asked Questions about attractor-metadynamics-neural

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How does slow adaptation shape neural attractor landscapes?▼

Slow adaptation shapes neural attractor landscapes by gradually modifying neural dynamics to alter stable states. This framework provides a Python-based approach to simulate plasticity and visualize how attractor landscapes evolve during continuous learning.

How do I simulate attractor dynamics with meta-dynamics in Python?▼

You simulate attractor dynamics with meta-dynamics using the provided Python API. Running the example with default parameters visualizes attractor landscape evolution, offering a straightforward way to model neural dynamics and plasticity without complex setup.

Can I analyze long-term memory stability in continuous learning scenarios?▼

Yes, you can analyze long-term memory stability in continuous learning scenarios. The framework supports evaluating how slow adaptation maintains stable neural attractor states over extended periods, helping assess memory retention within dynamical systems.

What is the best way to visualize neural attractor evolution during plasticity?▼

Visualizing neural attractor evolution during plasticity is best handled through a metadynamics framework. This Python-based tool simulates slow adaptation and generates visualizations of the changing attractor landscape, making the dynamical transformations explicit.

Do I need specific dependencies to run the neural dynamics simulation?▼

No specific dependencies are required to run the neural dynamics simulation. The framework is self-contained with a Python implementation, allowing you to simulate dynamics and visualize attractor evolution using the simple API provided.