> ## Documentation Index
> Fetch the complete documentation index at: https://ai.teamjaaf.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Machine Learning

> Comprehensive guide to Machine Learning — covering all types, paradigms, and algorithms with examples.

# 🤖 Machine Learning

***If you spot any errors, feel free to drop me a note at [mjh@teamjaaf.com](mailto:mjh@teamjaaf.com).***

Machine Learning (ML) is the **core engine** of modern AI systems.\
This page is your structured **gateway** to every major ML paradigm, from beginner-friendly algorithms to specialized and cutting-edge methods.

***

## 📌 What You’ll Explore

<Columns cols={2}>
  <Card title="Supervised Learning" icon="tasks" href="/machine-learning/supervised/">
    Learn models trained on labeled data — including regression, classification, and sequence prediction.
  </Card>

  <Card title="Unsupervised Learning" icon="eye-slash" href="/machine-learning/unsupervised/">
    Discover clustering, dimensionality reduction, and anomaly detection.
  </Card>

  <Card title="Semi-Supervised Learning" icon="adjust" href="/machine-learning/semi-supervised/">
    Techniques that leverage small labeled datasets with large unlabeled ones.
  </Card>

  <Card title="Self-Supervised Learning" icon="infinity" href="/machine-learning/self-supervised/">
    Learn how modern foundation models pre-train using the data itself as supervision.
  </Card>

  <Card title="Reinforcement Learning (RL)" icon="gamepad" href="/machine-learning/rl/">
    Agents that learn via trial-and-error, rewards, and penalties.
  </Card>

  <Card title="Online Learning" icon="sync" href="/machine-learning/online/">
    Train models incrementally as new data arrives.
  </Card>

  <Card title="Ensemble Learning" icon="layer-group" href="/machine-learning/ensemble/">
    Boost accuracy with methods like bagging, boosting, and stacking.
  </Card>

  <Card title="Evolutionary Algorithms" icon="dna" href="/machine-learning/evolutionary/">
    Optimization inspired by natural selection, genetic algorithms, and swarm intelligence.
  </Card>

  <Card title="Probabilistic Models" icon="dice" href="/machine-learning/probabilistic/">
    Bayesian networks, Markov models, and statistical inference.
  </Card>

  <Card title="Graph Machine Learning" icon="project-diagram" href="/machine-learning/graph/">
    Learn algorithms for graph-structured data, including GNNs and link prediction.
  </Card>

  <Card title="Meta-Learning" icon="brain" href="/machine-learning/meta/">
    "Learning to learn" — models that adapt quickly to new tasks.
  </Card>
</Columns>

***

## 🗂 ML Types Overview

| Category            | Description                              | Example Algorithms                                     |
| ------------------- | ---------------------------------------- | ------------------------------------------------------ |
| **Supervised**      | Learns from labeled datasets.            | Linear Regression, SVM, Random Forest, Neural Networks |
| **Unsupervised**    | Finds hidden patterns in unlabeled data. | K-Means, DBSCAN, PCA, t-SNE                            |
| **Semi-Supervised** | Mix of labeled and unlabeled data.       | Semi-Supervised SVM, Ladder Networks                   |
| **Self-Supervised** | Generates labels from data itself.       | BERT, SimCLR, BYOL                                     |
| **Reinforcement**   | Learns via interaction & rewards.        | Q-Learning, PPO, DQN                                   |
| **Online Learning** | Updates model with incoming data.        | Stochastic Gradient Descent, Passive-Aggressive        |
| **Ensemble**        | Combines multiple models.                | Bagging, AdaBoost, XGBoost                             |
| **Evolutionary**    | Nature-inspired optimization.            | Genetic Algorithms, Particle Swarm Optimization        |
| **Probabilistic**   | Models uncertainty and inference.        | Bayesian Networks, HMM                                 |
| **Graph ML**        | Works with graph-structured data.        | GCN, GraphSAGE                                         |
| **Meta-Learning**   | Few-shot, adaptable learning.            | MAML, Reptile                                          |

***

## 📚 Where to Go Next

* 📄 [Supervised Learning Guide](/machine-learning/supervised/)
* 📄 [Unsupervised Learning Guide](/machine-learning/unsupervised/)
* 📄 [Reinforcement Learning Guide](/machine-learning/rl/)

***

Built by [**Mohammad Jafrin Hossain**](https://www.linkedin.com/in/md-jafrin-hossain/) — part of the **AI Pathway** series.

***