AsterMind-ELM: Modular Extreme Learning Machine for On-Device ML in JS/TS

Introduction

AsterMind-ELM is a modular Extreme Learning Machine (ELM) library for JavaScript and TypeScript, designed for instant, tiny, on-device machine learning in web and Node.js environments. It enables models that train in milliseconds, predict with microsecond latency, and run entirely in the browser, eliminating the need for GPUs, servers, or external tracking.

With features like Kernel ELMs, Online ELM, DeepELM, and Web Worker offloading, developers can create private classifiers, real-time retrieval systems, interactive creative tools, and edge analytics solutions. ELMs provide closed-form training, interpretable structure, and tiny memory footprints, and AsterMind enhances these with modern capabilities for seriously fast and practical ML in web apps.

Key Features

AsterMind-ELM offers a rich set of features to empower your on-device ML projects:

• Modular Architecture
• Closed-form training (ridge / pseudoinverse)
• Kernel ELM with Nyström and whitening
• Online ELM (RLS) with forgetting factor
• DeepELM (stacked layers)
• Web Worker adapter for off-main-thread operations
• Embeddings and Chains for retrieval and deep pipelines
• JSON import/export for model persistence
• Zero server/GPU, enabling private, on-device ML
• Lightweight deployment (ESM + UMD)
• Embedding Store for efficient vector search

Installation

NPM (scoped package):

npm install @astermind/astermind-elm
# or
pnpm add @astermind/astermind-elm
# or
yarn add @astermind/astermind-elm

CDN / <script> (UMD global astermind):

<script src="https://cdn.jsdelivr.net/npm/@astermind/astermind-elm/dist/astermind.umd.js" target="_blank"></script>


<script src="https://unpkg.com/@astermind/astermind-elm/dist/astermind.umd.js" target="_blank"></script>

<script>
  const { ELM, KernelELM } = window.astermind;
</script>

Usage Examples

Basic ELM Classifier

import { ELM } from "@astermind/astermind-elm";

const config = { categories: ['English', 'French'], hiddenUnits: 128 };
const elm = new ELM(config);

// Load or train logic here
const results = elm.predict("bonjour");
console.log(results);

For more advanced examples, including Kernel ELM and DeepELM, please refer to the project's GitHub repository.

Why Use AsterMind?

AsterMind empowers you to build AI systems that are:

• Decentralized.
• Self-healing and retrain independently.
• Capable of running directly in the browser.
• Transparent and interpretable.

Links

• GitHub Repository: https://github.com/infiniteCrank/AsterMind-ELM
• NPM Package: https://www.npmjs.com/package/@astermind/astermind-elm