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

# Machine Learning Syllabus

> Overview, schedule, grading, and logistics for the Introduction to Machine Learning course.

<img src="https://mintcdn.com/aegeanaiinc/0dr6ajwzGFHGACv0/courses/ml/images/llama-datasets.png?fit=max&auto=format&n=0dr6ajwzGFHGACv0&q=85&s=6073ed9f7e16a7b77838cfb07ac446af" alt="Introduction to Machine Learning" style={{width: '100%', maxHeight: '400px', objectFit: 'cover', borderRadius: '8px'}} width="2816" height="1536" data-path="courses/ml/images/llama-datasets.png" />

## What this course is all about

This course builds machine learning from its statistical foundations up to modern deep learning. You start by refreshing the probability that underpins every model, then work through the supervised learning problem: linear regression, stochastic gradient descent, maximum likelihood, and classification with logistic regression. From there you move into deep neural networks, from the perceptron and backpropagation to convolutional networks for vision, and you close with sequence models and the Transformer architecture behind today's language models.

Each week pairs the theory in the lecture notes with hands-on reading and runnable notebooks from Aurélien Géron's *Hands-On Machine Learning with Scikit-Learn and PyTorch*, so every concept is something you can run, change, and inspect for yourself. The [weekly study guide](/courses/ml/study-guides/weekly-guide) lays out the week-by-week lectures, videos, textbook chapters, and assignments.

## Topics Covered

<CardGroup cols={2}>
  <Card title="Statistical Learning Theory" icon="chart-line" href="/aiml-common/lectures/learning-problem/index">
    The learning problem, entropy, optimization fundamentals, and classification basics.
  </Card>

  <Card title="Deep Neural Networks" icon="brain" href="/aiml-common/lectures/dnn/dnn-intro/index">
    Fundamentals of deep learning, network architectures, forward propagation, and backpropagation.
  </Card>

  <Card title="Large Language Models" icon="message" href="/aiml-common/lectures/llm/index">
    RNNs, LSTMs, transformers, and self-attention mechanisms for language understanding.
  </Card>
</CardGroup>

## Books

1. **GERON** - [Hands-On Machine Learning with Scikit-Learn and PyTorch](https://learning.oreilly.com/library/view/hands-on-machine-learning/9798341607972/), Oct 2025, Free for NJIT students. Very useful for those new to numerical Python and Pytorch.

2. **DL** - [Deep Learning](https://www.deeplearningbook.org/). This book provides the necessary depth for statistical learning concepts in this course.

## Planned Schedule

See the [weekly study guide](/courses/ml/study-guides/weekly-guide) for the week-by-week plan. If your semester is compressed to 4-5 weeks, each calendar week covers two units.

## Class Schedule

### Online Section

| Institution | Course Code | Schedule               | Location |
| ----------- | ----------- | ---------------------- | -------- |
| NJIT        | CS-375-451  | Mondays, 6:00pm-7:00pm | Zoom     |

## Communication

<Card title="Discord" icon="discord" href="https://discord.gg">
  Primary channel for all communication and questions related to lectures and projects. Please install Discord on your smartphones as well. Info has been sent via Canvas/Brightspace.
</Card>

### Support

Use the Discord ticketing system for:

* Grading issues
* Private matters requiring staff or professor response

All tickets are private between student and staff/professor.

## Office Hours

On-demand office hours coordinated via Discord:

1. Direct message the professor to arrange a 30-minute slot
2. Once agreed, send a [Google Calendar invitation](https://support.google.com/meet/answer/9302870?hl=en\&co=GENIE.Platform%3DDesktop) with Google Meet info (no Zoom please)
3. Include in your invitation the questions/issues you want to discuss so we can have a productive meeting

## Grading

| Component   | Weight |
| ----------- | ------ |
| Assignments | 40%    |
| Project     | 30%    |
| Final       | 30%    |

### Late Policy

* Assignments submitted within 24 hours of the deadline: 10% penalty
* Assignments submitted within 48 hours of the deadline: 25% penalty
* No submissions accepted after 48 hours without prior approval. Health related issues must be directed to the University and never sent to the staff.

## Staff

### Instructor

Pantelis Monogioudis, Ph.D.

### Teaching Assistants

They have introduced themselves on Discord, here is the list.

| Course | TA     |
| ------ | ------ |
| CS375  | Hao Xu |

## Academic Integrity

All submitted work must be your own. You may discuss concepts with classmates, but all code and written work must be completed independently unless explicitly stated otherwise.

Use of AI assistants (e.g., ChatGPT, Claude, GitHub Copilot) is permitted for learning and debugging, but you must:

1. Understand all code you submit
2. Be able to explain your solutions
3. Cite any AI-assisted portions

## Required Tools

* Python 3.11+
* Docker
* Git/GitHub
* VS Code (recommended) or your preferred IDE
* Hugging Face account

See the [Development Environment Guide](/aiml-common/resources/environment/index) for setup instructions.

***

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