@astermind/astermind-community

v3.0.0

Published

7 days ago

AsterMind Community - Complete ELM library with 21+ advanced variants, Pro features (RAG, reranking, summarization), and OmegaSynth synthetic data generation. Free and open-source. Combines all features from AsterMind-ELM, AsterMind-Pro, AsterMind-Premium

AsterMind-Community

Complete ELM library with 21+ advanced variants, Pro features (RAG, reranking, summarization), and OmegaSynth synthetic data generation. Free and open-source.

AsterMind Community combines all features from AsterMind-ELM, AsterMind-Pro, AsterMind-Premium, and AsterMind-Synth into one unified, free, and open-source package under the MIT license.

🚀 What you can build — and why this is groundbreaking

AsterMind brings instant, tiny, on-device ML to the web. It lets you ship models that train in milliseconds, predict with microsecond latency, and run entirely in the browser — no GPU, no server, no tracking. With Kernel ELMs, Online ELM, DeepELM, and Web Worker offloading, you can create:

Private, on-device classifiers (language, intent, toxicity, spam) that retrain on user feedback
Real-time retrieval & reranking with compact embeddings (ELM, KernelELM, Nyström whitening) for search and RAG
Interactive creative tools (music/drum generators, autocompletes) that respond instantly
Edge analytics: regressors/classifiers from data that never leaves the page
Deep ELM chains: stack encoders → embedders → classifiers for powerful pipelines, still tiny and transparent

Why it matters: ELMs give you closed-form training (no heavy SGD), interpretable structure, and tiny memory footprints.
AsterMind modernizes ELM with kernels, online learning, workerized training, robust preprocessing, and deep chaining — making seriously fast ML practical for every web app.

🆕 New in v3.0.0 - Unified Community Edition

Major Release: All features from Elm, Pro, Premium, and Synth are now free and open-source!

21 Advanced ELM Variants — Previously Premium-only, now free:
- Adaptive Online ELM, Forgetting Online ELM, Hierarchical ELM
- Attention-Enhanced ELM, Variational ELM, Time-Series ELM
- Transfer Learning ELM, Graph ELM, Graph Kernel ELM
- Adaptive Kernel ELM, Sparse Kernel ELM, Ensemble Kernel ELM
- Deep Kernel ELM, Robust Kernel ELM, ELM-KELM Cascade
- String Kernel ELM, Convolutional ELM, Recurrent ELM
- Fuzzy ELM, Quantum-Inspired ELM, Tensor Kernel ELM
Pro Features — RAG, Reranking, Summarization, Information Flow Analysis (now free!)
OmegaSynth — Label-conditioned synthetic data generation (now free!)
All Core Features — Kernel ELMs, Online ELM, DeepELM, Web Workers, and more
MIT License — Fully open-source, no license required!

See Releases for full changelog.

📑 Table of Contents

🌟 AsterMind: Decentralized ELM Framework Inspired by Nature

Welcome to AsterMind, a modular, decentralized ML framework built around cooperating Extreme Learning Machines (ELMs) that self-train, self-evaluate, and self-repair — like the nervous system of a starfish.

How This ELM Library Differs from a Traditional ELM

This library preserves the core Extreme Learning Machine idea — random hidden layer, nonlinear activation, closed-form output solve — but extends it with:

Multiple activations (ReLU, LeakyReLU, Sigmoid, Linear, GELU)
Xavier/Uniform/He initialization
Dropout on hidden activations
Sample weighting
Metrics gate (RMSE, MAE, Accuracy, F1, Cross-Entropy, R²)
JSON export/import
Model lifecycle management
UniversalEncoder for text (char/token)
Data augmentation utilities
Chaining (ELMChain) for stacked embeddings
Weight reuse (simulated fine-tuning)
Logging utilities

AsterMind is designed for:

Lightweight, in-browser ML pipelines
Transparent, interpretable predictions
Continuous, incremental learning
Resilient systems with no single point of failure

✨ Features

Core Features

✅ Modular Architecture
✅ Closed-form training (ridge / pseudoinverse)
✅ Activations: relu, leakyrelu, sigmoid, tanh, linear, gelu
✅ Initializers: uniform, xavier, he
✅ Numeric + Text configs
✅ Kernel ELM with Nyström + whitening
✅ Online ELM (RLS) with forgetting factor
✅ DeepELM (stacked layers)
✅ Web Worker adapter
✅ Embeddings & Chains for retrieval and deep pipelines
✅ JSON import/export
✅ Self-governing training
✅ Flexible preprocessing
✅ Lightweight deployment (ESM + UMD)
✅ Retrieval and classification utilities
✅ Zero server/GPU — private, on-device ML

Advanced ELM Variants (21 variants, now free!)

✅ Adaptive Online ELM, Forgetting Online ELM
✅ Hierarchical ELM, Attention-Enhanced ELM, Variational ELM
✅ Time-Series ELM, Transfer Learning ELM
✅ Graph ELM, Graph Kernel ELM
✅ Adaptive/Sparse/Ensemble/Deep/Robust Kernel ELM
✅ ELM-KELM Cascade, String Kernel ELM
✅ Convolutional ELM, Recurrent ELM
✅ Fuzzy ELM, Quantum-Inspired ELM, Tensor Kernel ELM

Pro Features (now free!)

✅ RAG Pipeline (Retrieval-Augmented Generation)
✅ Reranking
✅ Summarization
✅ Information Flow Analysis
✅ Transfer Entropy

Synthetic Data Generation (now free!)

✅ OmegaSynth - Label-conditioned synthetic data generation
✅ Multiple generation modes (retrieval, ELM, hybrid, exact, perfect)
✅ Pattern correction and sequence context
✅ Character embeddings

🧠 Kernel ELMs (KELM)

Supports Exact and Nyström modes with RBF/Linear/Poly/Laplacian/Custom kernels.
Includes whitened Nyström (persisted whitener for inference parity).

import { KernelELM, KernelRegistry } from '@astermind/astermind-elm';

const kelm = new KernelELM({
  outputDim: Y[0].length,
  kernel: { type: 'rbf', gamma: 1 / X[0].length },
  mode: 'nystrom',
  nystrom: { m: 256, strategy: 'kmeans++', whiten: true },
  ridgeLambda: 1e-2,
});
kelm.fit(X, Y);

🔁 Online ELM (OS-ELM)

Stream updates via Recursive Least Squares (RLS) with optional forgetting factor. Supports He/Xavier/Uniform initializers.

import { OnlineELM } from '@astermind/astermind-elm';
const ol = new OnlineELM({ inputDim: D, outputDim: K, hiddenUnits: 256 });
ol.init(X0, Y0);
ol.update(Xt, Yt);
ol.predictProbaFromVectors(Xq);

Notes

forgettingFactor controls how fast older observations decay (default 1.0).
Two natural embedding modes: hidden (activations) or logits (pre-softmax). Use with ELMAdapter (see below).

🌊 DeepELM

Stack multiple ELM layers for deep nonlinear embeddings and an optional top ELM classifier.

import { DeepELM } from '@astermind/astermind-elm';
const deep = new DeepELM({
  inputDim: D,
  layers: [{ hiddenUnits: 128 }, { hiddenUnits: 64 }],
  numClasses: K
});
// 1) Unsupervised layer-wise training (autoencoders Y=X)
const X_L = deep.fitAutoencoders(X);
// 2) Supervised head (ELM) on last layer features
deep.fitClassifier(X_L, Y);
// 3) Predict
const probs = deep.predictProbaFromVectors(Xq);

JSON I/O
toJSON() and fromJSON() persist the full stack (AEs + classifier).

🧵 Web Worker Adapter

Move heavy ops off the main thread. Provides ELMWorker + ELMWorkerClient for RPC-style training/prediction with progress events.

Initialize with initELM(config) or initOnlineELM(config)
Train via train / trainFromData / fit / update
Predict via predict, predictFromVector, or predictLogits
Subscribe to progress callbacks per call

See Workers for full API.

🚀 Installation

NPM (scoped package):

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

CDN / <script> (UMD global astermind):

<!-- jsDelivr -->
<script src="https://cdn.jsdelivr.net/npm/@astermind/astermind-community/dist/astermind.umd.js"></script>

<!-- or unpkg -->
<script src="https://unpkg.com/@astermind/astermind-community/dist/astermind.umd.js"></script>

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

Repository:

GitHub: https://github.com/infiniteCrank/AsterMind-Community
NPM: https://www.npmjs.com/package/@astermind/astermind-community

Migration from old packages:

See Migration Guide for details
All old packages (@astermind/astermind-elm, @astermind/astermind-pro, @astermind/astermind-premium, @astermind/astermind-synthetic-data) are deprecated
Simply install @astermind/astermind-community and update your imports - no license required!

🛠️ Usage Examples

Basic ELM Classifier

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

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);

Advanced ELM Variants (Now Free!):

import { AdaptiveOnlineELM, HierarchicalELM, TimeSeriesELM } from "@astermind/astermind-community";

// Adaptive Online ELM - dynamically adjusts hidden units
const adaptive = new AdaptiveOnlineELM({
  categories: ['class1', 'class2'],
  initialHiddenUnits: 128
});

// Hierarchical ELM - multi-level classification
const hierarchical = new HierarchicalELM({
  hierarchy: { 'root': ['animal', 'plant'], 'animal': ['mammal', 'bird'] },
  rootCategories: ['root']
});

// Time-Series ELM - specialized for sequential data
const timeSeries = new TimeSeriesELM({
  categories: ['trend_up', 'trend_down', 'stable'],
  sequenceLength: 10
});

Synthetic Data Generation (Now Free!):

import { OmegaSynth } from "@astermind/astermind-community";

const synth = new OmegaSynth({
  mode: 'hybrid', // or 'elm', 'exact', 'retrieval', 'perfect'
  maxLength: 32
});

await synth.train(dataset);
const generated = await synth.generate('label', 10);

CommonJS / Node:

const { ELM, AdaptiveOnlineELM, OmegaSynth } = require("@astermind/astermind-community");

Kernel ELM / DeepELM: see above examples.

🧪 Suggested Experiments

Compare retrieval performance with Sentence-BERT and TFIDF.
Experiment with activations and token vs char encoding.
Deploy in-browser retraining workflows.

🌿 Why Use AsterMind?

Because you can build AI systems that:

Are decentralized.
Self-heal and retrain independently.
Run in the browser.
Are transparent and interpretable.

📚 Core API Documentation

ELM

train, trainFromData, predict, predictFromVector, getEmbedding, predictLogitsFromVectors, JSON I/O, metrics
loadModelFromJSON, saveModelAsJSONFile
Evaluation: RMSE, MAE, Accuracy, F1, Cross-Entropy, R²
Config highlights: ridgeLambda, weightInit (uniform | xavier | he), seed

OnlineELM

init, update, fit, predictLogitsFromVectors, predictProbaFromVectors, embeddings (hidden/logits), JSON I/O
Config highlights: inputDim, outputDim, hiddenUnits, activation, ridgeLambda, forgettingFactor

KernelELM

fit, predictProbaFromVectors, getEmbedding, JSON I/O
mode: 'exact' | 'nystrom', kernels: rbf | linear | poly | laplacian | custom

DeepELM

fitAutoencoders(X), transform(X), fitClassifier(X_L, Y), predictProbaFromVectors(X)
toJSON(), fromJSON() for full-pipeline persistence

ELMChain

sequential embeddings through multiple encoders

TFIDFVectorizer

vectorize, vectorizeAll

KNN

find(queryVec, dataset, k, topX, metric)

📘 Method Options Reference

`train(augmentationOptions?, weights?)`

augmentationOptions: { suffixes, prefixes, includeNoise }
weights: sample weights

`trainFromData(X, Y, options?)`

X: Input matrix
Y: Label matrix or one-hot
options: { reuseWeights, weights }

`predict(text, topK)`

text: string
topK: number of predictions

`predictFromVector(vector, topK)`

vector: numeric
topK: number of predictions

`saveModelAsJSONFile(filename?)`

filename: optional file name

⚙️ ELMConfig Options Reference

| Option | Type | Description | | -------------------- | ---------- | ------------------------------------------------------------- | | categories | string[] | List of labels the model should classify. (Required) | | hiddenUnits | number | Number of hidden layer units (default: 50). | | maxLen | number | Max length of input sequences (default: 30). | | activation | string | Activation function (relu, tanh, etc.). | | encoder | any | Custom UniversalEncoder instance (optional). | | charSet | string | Character set used for encoding. | | useTokenizer | boolean | Use token-level encoding. | | tokenizerDelimiter | RegExp | Tokenizer regex. | | exportFileName | string | Filename to export JSON. | | metrics | object | Thresholds (rmse, mae, accuracy, etc.). | | log | object | Logging config. | | dropout | number | Dropout rate. | | weightInit | string | Initializer. (uniform | xavier | he) | | ridgeLambda | number | Ridge penalty for closed-form solve. | | seed | number | PRNG seed for reproducibility. |

🧩 Prebuilt Modules and Custom Modules

Includes: AutoComplete, EncoderELM, CharacterLangEncoderELM, FeatureCombinerELM, ConfidenceClassifierELM, IntentClassifier, LanguageClassifier, VotingClassifierELM, RefinerELM.

Each exposes .train(), .predict(), .loadModelFromJSON(), .saveModelAsJSONFile(), .encode().

Custom modules can be built on top.

✨ Text Encoding Modules

Includes TextEncoder, Tokenizer, UniversalEncoder.
Supports char-level & token-level, normalization, n-grams.

🖥️ UI Binding Utility

bindAutocompleteUI(model, inputElement, outputElement, topK) helper.
Binds model predictions to live HTML input.

✨ Data Augmentation Utilities

Augment with prefixes, suffixes, noise.
Example: Augment.generateVariants("hello", "abc", { suffixes:["world"], includeNoise:true }).

⚠️ IO Utilities (Experimental)

JSON/CSV/TSV import/export, schema inference.
Experimental and may be unstable.

🧰 Embedding Store

Lightweight vector store with cosine/dot/euclidean KNN, unit-norm storage, ring buffer capacity.

Usage

import { EmbeddingStore } from '@astermind/astermind-elm';

const store = new EmbeddingStore({ capacity: 5000, normalize: true });
store.add({ id: 'doc1', vector: [/* ... */], meta: { title: 'Hello' } });
const hits = store.query({ vector: q, k: 10, metric: 'cosine' });

🔧 Utilities: Matrix & Activations

Matrix – internal linear algebra utilities (multiply, transpose, addRegularization, solveCholesky, etc.).
Activations – relu, leakyrelu, sigmoid, tanh, linear, gelu, plus softmax, derivatives, and helpers (get, getDerivative, getPair).

🔗 Adapters & Chains

ELMAdapter wraps an ELM or OnlineELM to behave like an encoder for ELMChain:

import { ELMAdapter, wrapELM, wrapOnlineELM } from '@astermind/astermind-elm';

const enc1 = wrapELM(elm);                          // uses elm.getEmbedding(X)
const enc2 = wrapOnlineELM(online, { mode: 'logits' }); // 'hidden' or 'logits'
const chain = new ELMChain([enc1, enc2], { normalizeFinal: true });

const Z = chain.getEmbedding(X); // stacked embeddings

🧱 Workers: ELMWorker & ELMWorkerClient

ELMWorker (inside a Web Worker) exposes a tolerant RPC surface:

lifecycle: initELM, initOnlineELM, dispose, getKind, setVerbose
training: train, fit, update, trainFromData (all routed appropriately)
prediction: predict, predictFromVector, predictLogits
progress events: { type:'progress', phase, pct } during training

ELMWorkerClient (on the main thread) is a thin promise-based RPC client:

import { ELMWorkerClient } from '@astermind/astermind-elm/worker';

const client = new ELMWorkerClient(new Worker(new URL('./ELMWorker.js', import.meta.url)));
await client.initELM({ categories:['A','B'], hiddenUnits:128 });

await client.elmTrain({}, (p) => console.log(p.phase, p.pct));
const preds = await client.elmPredict('bonjour', 5);

🧪 Example Demos and Scripts

Run with npm run dev:* (autocomplete, lang, chain, news).
Fully in-browser.

🧪 Experiments and Results

Includes dropout tuning, hybrid retrieval, ensemble distillation, multi-level pipelines.
Results reported (Recall@1, Recall@5, MRR).

📚 Documentation

AsterMind ELM includes comprehensive documentation to help you get started and master the library:

Getting Started

Quick Start Tutorial — Complete step-by-step guide covering all major features with practical examples
- Basic ELM, Kernel ELM, Online ELM, DeepELM
- Embeddings, ELM Chains, Web Workers
- Pre-built modules, model persistence
- Advanced features and troubleshooting
AsterMind ELM Overview — High-level overview of what AsterMind ELM is and why tiny neural networks matter
- Core capabilities (classification, regression, embeddings, online learning)
- The AsterMind ecosystem
- Technical architecture overview

Implementation & Integration

Implementation Models — Guide to different ways of implementing AsterMind
- SDK/Library Implementation: Integrating AsterMind into your applications
- Standalone Applications: Using pre-built example applications
- Service Engagement: Professional services for custom implementation
- How to choose the right approach for your needs
Technical Requirements — System requirements for different platforms
- Windows, Linux, and macOS requirements
- Browser compatibility
- Development and runtime requirements
- Troubleshooting common issues

Developer Resources

Code Walkthrough — Detailed code walkthrough for presentations and deep dives
- Entry points and exports
- Core architecture and configuration system
- Main ELM class implementation
- Training and prediction flows
- Key code snippets with line numbers
Data Requirements — Guide to data requirements for training models
- Minimum viable data sizes
- Recommendations for better generalization
- Data collection strategies
- ELM-specific considerations

Additional Resources

Examples Directory — Working demo applications
- Language classification
- Autocomplete chains
- News classification
- Music genre detection
- And more...
Node Examples — Advanced Node.js examples
- Two-stage retrieval systems
- TF-IDF integration
- DeepELM + KernelELM retrieval
- Experimental architectures
Legal Information — Licensing, patents, and legal notices

Documentation Quick Links

| Document | Purpose | Audience | |----------|---------|----------| | Quick Start Tutorial | Learn how to use all features | Beginners | | Overview | Understand what AsterMind is | Everyone | | Implementation Models | Choose integration approach | Decision makers, developers | | Technical Requirements | System setup and requirements | DevOps, developers | | Code Walkthrough | Deep dive into code structure | Developers, presenters | | Data Requirements | Training data guidelines | ML practitioners |

📦 Releases

v2.1.0 — 2026-09-19

New features: Kernel ELM, Nyström whitening, OnlineELM, DeepELM, Worker adapter, EmbeddingStore 2.0, activations linear/gelu, config split.
Fixes: Xavier init, encoder guards, dropout scaling.
Breaking: Config now NumericConfig|TextConfig.

📄 License

MIT License

All features are now free and open-source! This package combines all features from the previous AsterMind packages (ELM, Pro, Premium, Synth) into one unified community edition under the MIT license. No license tokens or subscriptions required.

“AsterMind doesn’t just mimic a brain—it functions more like a starfish: fully decentralized, self-evaluating, and self-repairing.”