Hyperparameter Search

Community

Efficiently tune BrainAI hyperparameters.

Authorsovr610
Version1.0.0
Installs0

System Documentation

What problem does it solve?

BrainAI hyperparameter tuning is complex due to multi-phase training, conditional parameters, and expensive evaluations; this skill provides an automated, reproducible workflow to discover effective configurations.

Core Features & Use Cases

  • Phase-by-phase HPO for SNN, Encoders, HTM, Workspace, Decision, Reasoning, and Meta phases.
  • LR finder integration to prune the search space by learning rate bounds.
  • Bayesian optimization (TPE) and ASHA-based pruning with warm-starts and presets tailored for phase-specific tuning.
  • Experiment logging, parameter importance estimation, and CSV export for analysis.

Quick Start

Run LR range test to bound learning rate and then launch a Bayesian optimization run with ASHA pruning for phase-wise BrainAI configurations.

Dependency Matrix

Required Modules

torch

Components

scriptsreferencesassets

💻 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: Hyperparameter Search
Download link: https://github.com/sovr610/refffiy/archive/main.zip#hyperparameter-search

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.