skills.rest
hiyenwong
hiyenwongCOMMUNITY
Explore all skills by this author →
𝕏@khonsu_51GitHub

jedi-neural-dynamics-inference

Infer task-aware neural dynamics by embedding task contexts and adapting RNN weights.

2|Updated Feb 12, 2026
Search Tags:#eigenvalues#neural dynamics#multi-task learning#embedded rnn#task embeddings#dynamics analysis#fixed points
One-click install
npx skills add https://github.com/hiyenwong/ai_collection --skill jedi-neural-dynamics-inference
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jedi-neural-dynamics-inference
Source: https://github.com/hiyenwong/ai_collection/tree/main/collection/skills/jedi-neural-dynamics-inference
Command: npx skills add https://github.com/hiyenwong/ai_collection --skill jedi-neural-dynamics-inference

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Translates the challenge of identifying task-specific neural dynamics from limited, noisy, high-dimensional neural data into a unified, learnable framework.

Core Features & Use Cases

  • Task-embedded RNNs: generate task-conditioned weights from learned embeddings.
  • Cross-task dynamics analysis: extract eigenvalues, fixed points, and spectral radius to interpret dynamics.
  • Multi-task neuroscience modeling: apply to motor cortex data and population dynamics studies.

Quick Start

Provide neural data and a task_id to train the model and start extracting task-specific dynamics.

Frequently Asked Questions about jedi-neural-dynamics-inference

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

FAQPage Schema
How do I infer task-specific neural dynamics from multi-task population recordings?▼

You can infer task-specific neural dynamics by jointly embedding task contexts and adapting RNN weights, which maps learned task embeddings to network parameters for analyzing multi-task neural data.

What is the best way to extract eigenvalues and fixed points from multi-task neural data?▼

Extracting eigenvalues and fixed points from multi-task neural data requires training a task-embedded RNN with an evaluation routine that computes spectral radius and dynamics from the adapted weights.

How does a task-embedded RNN model handle multi-task learning for motor cortex data?▼

A task-embedded RNN handles multi-task learning by using a weight generator that maps a dedicated embedding layer per task to RNN parameters, enabling task-conditioned weight generation for motor cortex data.

Can I analyze cross-task dynamics and spectral radius using neural population dynamics modeling?▼

Yes, you can analyze cross-task dynamics and spectral radius by providing neural data and a task identifier to train the model, which returns eigenvalues and fixed points for population dynamics interpretation.

Does neural dynamics inference require separate embeddings for each task context?▼

Yes, neural dynamics inference requires a separate embedding layer per task context, which the weight generator maps to RNN parameters to adapt the network for each specific task.

Why use task embeddings for RNN weight generation in noisy high-dimensional neural data?▼

Task embeddings translate the challenge of identifying task-specific dynamics from limited, noisy, high-dimensional neural data into a unified, learnable framework by generating task-conditioned RNN weights.

Related Skills

Explore More Data & Analytics Skills→
hiyenwonghiyenwong
2

cornn-convex-rnn-optimization

Convert non-convex RNN training into a convex optimization problem with cvxpy.

Community
Advanced
hiyenwonghiyenwong
2

neural-code-dynamics-analysis

Analyze neural code dynamics to identify criticality signatures across biological and artificial networks.

Community
Advanced
xjtulycxjtulyc
33

brian2-simulation

Simulate spiking neural networks with Brian2 for neuron dynamics and STDP analysis.

Community
Advanced
Qiuu2Qiuu2

DSPAlgorithmAgent_Skill

Develop fixed-point DSP algorithms for embedded audio DSP platforms.

Community
Advanced