temporal-attention-graph-neural

Community

Decode dynamic brain networks with attention

Authorhiyenwong
Version1.0.0
Installs0

System Documentation

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.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: temporal-attention-graph-neural
Download link: https://github.com/hiyenwong/ai_collection/archive/main.zip#temporal-attention-graph-neural

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.