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

cornn-convex-rnn-optimization

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

2|Updated Feb 12, 2026
Search Tags:#real-time#machine-learning#cvxpy#rnn#neural-dynamics#convex-optimization#training-speed
One-click install
npx skills add https://github.com/hiyenwong/ai_collection --skill cornn-convex-rnn-optimization
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cornn-convex-rnn-optimization
Source: https://github.com/hiyenwong/ai_collection/tree/main/collection/skills/cornn-convex-rnn-optimization
Command: npx skills add https://github.com/hiyenwong/ai_collection --skill cornn-convex-rnn-optimization

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convex optimization converts non-convex RNN training into a convex formulation, dramatically speeding up training on standard hardware.

Core Features & Use Cases

  • Convexified RNN training enables rapid inference of neural dynamics.
  • Supports million-parameter RNNs on standard hardware.
  • Real-time network reconstruction for large-scale neural data.
  • Use cases include large-scale neural recordings, neural dynamics inference, and attractor structure recovery.

Quick Start

Provide neural_data and call cornn_train with chosen hidden_dim and regularization to train the CORNN model and inspect the resulting W_rec, W_in and dynamics.

Frequently Asked Questions about cornn-convex-rnn-optimization

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

FAQPage Schema
How does convex optimization speed up RNN training?▼

Convex optimization speeds up RNN training by converting the non-convex formulation into a convex problem, allowing rapid convergence and enabling million-parameter RNNs to train efficiently on standard hardware.

How do I train a convexified RNN using neural recordings?▼

To train a convexified RNN, provide your neural recordings as neural_data and call cornn_train with chosen hidden_dim and regularization parameters to return W_rec, W_in, and inferred dynamics.

Can I use cvxpy to infer real-time neural dynamics from large-scale recordings?▼

Yes, this Skill implements a convex formulation with cvxpy to process large-scale neural recordings, enabling real-time neural dynamics inference and rapid network reconstruction.

What is the best way to recover attractor structure from neural data?▼

Recovering attractor structure from neural data is best achieved by transforming non-convex RNN training into a convex optimization problem, which dramatically accelerates modeling and structure recovery.

Does this convex RNN formulation require specialized hardware to run?▼

No, the convex RNN formulation is designed to run on standard hardware, enabling rapid modeling of large-scale neural recordings and real-time dynamics inference without specialized hardware requirements.

Related Skills

Explore More Data & Analytics Skills→
hiyenwonghiyenwong
2

jedi-neural-dynamics-inference

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

Community
Advanced
hiyenwonghiyenwong
2

attractor-metadynamics-neural

Simulate neural attractor dynamics and plasticity with a Python framework.

Community
Intermediate
hiyenwonghiyenwong
2

temporal-attention-graph-neural

Model time-varying neuronal connectivity with probabilistic graph learning and temporal attention.

Community
Advanced
sandraschisandraschi
18

optimization-theory-expert

Solve optimization problems using linear programming, convex optimization, and gradient methods.

Community
Advanced