temporal-attention-graph-neural

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

2|Updated Feb 12, 2026

Search Tags:#neuroscience #graph-neural-networks #neural-dynamics #temporal-attention #variational-graph #behavior-decoding #time-varying-connectivity

Ready to run

npx skills add https://github.com/hiyenwong/ai_collection --skill temporal-attention-graph-neural

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Temporal dynamics of neuronal connections are challenging to capture. TAVRNN combines probabilistic graph learning with temporal attention to infer time-varying connectivity and relate it to behavior, delivering both single-unit dynamics and population-level explanations.

Core Features & Use Cases

Time-varying graph modeling: Learn dynamic adjacency matrices across time steps.
Explainable dynamics: Preserve neuron-level and group-level interpretability of connectivity changes.
Predictive decoding: Decode behavior from learned representations; supports behavior prediction and clustering.
Applications: Neural dynamics analysis, brain-machine interface development, and neuroscience discovery.

Quick Start

Train a TAVRNN on your neuronal activity sequence and inspect the learned time-varying graphs to interpret dynamic connectivity.

Frequently Asked Questions about temporal-attention-graph-neural

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

FAQPage Schema

How do I model time-varying neuronal connectivity from neural recordings?▼

You can model time-varying neuronal connectivity by applying probabilistic graph learning to neural recordings. This approach learns dynamic adjacency matrices across time steps to capture shifting brain network connections during behavior.

How does temporal attention help decode behavior from dynamic brain networks?▼

Temporal attention helps decode behavior by weighting specific time steps in neural activity sequences. It combines with latent connectivity inference to produce explainable representations that map dynamic brain networks to behavioral outputs.

Can I use graph neural networks for brain-machine interface development?▼

Yes, you can use graph neural networks for brain-machine interface development. They infer time-varying connectivity from neural recordings and generate interpretable dynamic graphs suitable for decoding behavior in brain-machine interface tasks.

What is the best way to infer latent connectivity while preserving neuron-level interpretability?▼

The best way to infer latent connectivity while preserving interpretability is using probabilistic graph learning with temporal attention. This method reconstructs dynamic graphs while maintaining both single-unit dynamics and population-level explanations.

Does variational graph learning support behavior prediction and clustering?▼

Yes, variational graph learning supports behavior prediction and clustering. It infers latent connectivity and applies time-aware attention to generate explainable representations that can be directly used for predictive decoding and clustering tasks.

When should I not use temporal attention graph models for neural dynamics analysis?▼

You should not use temporal attention graph models if your neural recordings lack temporal depth or if your analysis requires static connectivity assumptions. These models specifically target time-varying connectivity and dynamic behavior decoding tasks.