ljq2088

Emri ML Deeplearning — AI skill for Claude Code

AI community

ML/deep learning for EMRI waveform modeling, parameter estimation, population inference - main research direction.

How to install Emri ML Deeplearning

Installs to ~/.claude/skills/ljq2088-myclaude-emri-ml-deeplearning/SKILL.md

Terminal

mkdir -p ~/.claude/skills/ljq2088-myclaude-emri-ml-deeplearning && curl -fsSL https://raw.githubusercontent.com/ljq2088/MyClaude/HEAD/skills/emri-ml-deeplearning.md -o ~/.claude/skills/ljq2088-myclaude-emri-ml-deeplearning/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Emri ML Deeplearning does

name: emri-ml-deeplearning description: ML/deep learning for EMRI waveform modeling, parameter estimation, population inference - main research direction type: knowledge

EMRI x ML/Deep Learning

Key Bottleneck

14-dim parameter space, ~10^4-10^6 local maxima, single FEW waveform ~100ms -> standard MCMC needs 10^3-10^5 CPU hours.

ML role: **accelerate inference, not replace physics models**.

Simulation-Based Inference (Cole et al. 2025, 2505.16795)

Method: Truncated Marginal

Alternatives in AI

PyTorch Lightning — Deep learning with PyTorch Lightning framework 6.4k ★
Inference Serving — ai-research-skills vLLM, SGLang, TensorRT-LLM, llama.cpp 5.4k ★
Main — Open-source SaaS framework (React + Firebase + Stripe) with built-in Claude Code AI skills 550 ★