Skip to content

README.md

Latest commit

 

History

History
55 lines (41 loc) · 1.85 KB

README.md

File metadata and controls

55 lines (41 loc) · 1.85 KB

Week 1 - Machine Learning LS 2026

Home > Week 1

Learning Path

Week 1 has 4 topics that lay the groundwork for everything that follows. Work through them in order - each one is a prerequisite for the next.

Introduction to Machine Learning (Theory)
    |
    |  You need to know what ML is before you can build anything.
    v
Gradient Descent & Backpropagation
    |
    |  The core engine behind how every model learns from data.
    v
Environment & Programming Prerequisites
    |
    |  Python, NumPy, Pandas, Matplotlib - the tools you'll use daily.
    v
Data Pre-processing & Introduction to NLP
    |
    |  Real data is messy. Learn to clean it and convert text to numbers.
    v
Week 2

Topics

# Topic What You Will Learn Est. Time
1 Introduction to ML What ML is, supervised vs unsupervised learning, the ML lifecycle 2–3 hrs
2 Gradient Descent & Backpropagation Loss functions, gradient descent, SGD, backpropagation 3–4 hrs
3 Environment & Programming Prerequisites Google Colab, Python basics, NumPy, Pandas, Matplotlib 4–5 hrs
4 Data Pre-processing & Intro to NLP Train/val/test splits, text cleaning, tokenization basics 3–4 hrs

Before You Move to Week 2

  • Can you explain the difference between supervised and unsupervised learning?
  • Can you describe what gradient descent does in one sentence?
  • Can you load a CSV into Pandas, clean it, and plot a column with Matplotlib?
  • Can you explain what tokenization is and why it matters?

If yes, you are ready. See you in Week 2.

Home | Next: Week 2