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

# Courses

> AI and machine learning courses with structured learning paths

<div style={{display: 'flex', alignItems: 'center', gap: '2rem', marginBottom: '2rem', padding: '1.5rem', border: '2px solid var(--border-color, #e0e0e0)', borderRadius: '8px'}}>
  <img src="https://mintcdn.com/aegeanaiinc/fLxm5mHHjRRrjghy/images/book-cover.png?fit=max&auto=format&n=fLxm5mHHjRRrjghy&q=85&s=014e0871f080bed729c7c92c5c5bfda7" alt="Engineering AI Agents Book Cover" width="200" height="273" style={{flexShrink: 0, borderRadius: '4px', boxShadow: '0 2px 8px rgba(0,0,0,0.15)'}} data-path="images/book-cover.png" />

  <div>
    <h3 style={{marginTop: 0, marginBottom: '0.5rem'}}>From the Upcoming Book</h3>

    <p style={{marginBottom: '0.5rem'}}>
      All course materials are derived from our comprehensive book <strong><a href="/book/introduction">Engineering AI Agents</a></strong>, currently in development.
    </p>

    <p style={{margin: 0, fontSize: '0.9em', opacity: 0.8}}>
      These courses provide hands-on experience with the concepts, algorithms, and techniques that will be covered in depth in the book.
    </p>
  </div>
</div>

Our course offerings provide a comprehensive education in artificial intelligence, machine learning, and their applications. The curriculum is designed with a clear progression path to build foundational knowledge before advancing to specialized topics.

## Course Structure

Students typically begin with **Introduction to AI**, which establishes the fundamental concepts, techniques, and mathematical foundations necessary for advanced study. After completing the introductory course, students can choose to specialize in either **Deep Learning for Computer Vision** or **AI for Robotics**, based on their interests and career goals.

```mermaid theme={null}
graph TB
    AI["Introduction to AI<br/><em>Foundational Course</em>"]
    CV["Deep Learning for CV<br/><em>Specialization</em>"]
    Robotics["AI for Robotics<br/><em>Specialization</em>"]

    AI --> CV
    AI --> Robotics

    classDef foundation fill:#2F6868,stroke:#1C3C3C,stroke-width:3px,color:#fff
    classDef specialization fill:#84C4C0,stroke:#2F6868,stroke-width:2px,color:#1C3C3C

    class AI foundation
    class CV,Robotics specialization
```

## Prerequisites

Before starting any course, students should have a solid foundation in mathematics and programming. We recommend reviewing the following topics covered in our [Prerequisites](/book/prerequisites):

### Mathematical Foundations

* **Linear Algebra** - Vectors, matrices, eigenvalues, and matrix operations
* **Calculus** - Derivatives, gradients, and matrix calculus for optimization
* **Probability** - Joint, marginal, and conditional distributions

### Programming Skills

* **Python** - Proficiency in Python programming for data science and machine learning
* **Libraries** - Familiarity with PyTorch or TF/Keras, NumPy, Matplotlib, and other common MLframeworks

<Note>
  If you need to refresh your background knowledge, visit the [Prerequisites section](/book/prerequisites) for comprehensive reviews of these topics before beginning the coursework.
</Note>

## Spring 2026 Offerings

<CardGroup cols={2}>
  <Card title="CS-GY-6613, Introduction to AI" href="/courses/ai" icon="graduation-cap" cta="View course">
    Foundational concepts in artificial intelligence, machine learning, optimization, and neural networks. NYU Tandon.
  </Card>

  <Card title="CS681, Deep Learning for Computer Vision" href="/courses/cv" icon="eye" cta="View course">
    Advanced computer vision techniques including object detection, segmentation, and generative models. NJIT.
  </Card>

  <Card title="CS685, AI for Robotics" href="/courses/robotics" icon="robot" cta="View course">
    Intelligent robotic systems, ROS integration, perception motion planning, and vision-language-action models. NJIT.
  </Card>

  <Card title="CS670/370, Introduction to AI" href="/courses/ai" icon="graduation-cap" cta="View course">
    Foundational concepts in artificial intelligence, machine learning, optimization, and neural networks. NJIT.
  </Card>
</CardGroup>

## Learning Path

1. **Start with Introduction to AI** - Build your foundation in machine learning fundamentals, optimization techniques, and neural network architectures
2. **Choose your specialization** - Select either Computer Vision or Robotics based on your interests
3. **Apply your knowledge** - Complete hands-on assignments and projects throughout each course

## Course Resources

All courses include:

* Comprehensive lecture materials and readings
* Hands-on programming assignments
* Development environment setup guides
* Submission guidelines and best practices

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit this page on GitHub](https://github.com/aegean-ai/eaia/edit/main/src/courses/index.mdx) or [file an issue](https://github.com/aegean-ai/eaia/issues/new/choose).
</Callout>