Machine Learning from Scratch

Machine Learning from Scratch

2 weeks
16 Learners
Mar 13

Master the full ML pipeline, from linear algebra, calculus, and probability fundamentals to implementing regression, classification, clustering, and neural networks from scratch in NumPy, then scaling to scikit-learn, PyTorch, and real-world datasets with proper train/val/test splits, cross-validation, and model evaluation metrics.

Share:

W1

Week 1: ML Fundamentals & Algorithms from Scratch

By the end of this module you will be able to implement fundamental machine learning algorithms like Linear Regression, Logistic Regression, and K-Means clustering using only NumPy, demonstrating a deep understanding of their underlying mathematical principles.

7 videos
3 readings
7 topics
1 homework
Learn

Topics

1.1
Python for Data Science Essentials
1.2
Linear Algebra Essentials
1.3
Calculus Essentials
1.4
Probability & Statistics Basics
1.5
Linear Regression from Scratch
1.6
Logistic Regression from Scratch
1.7
K-Means Clustering from Scratch
W2

Week 2: Scaling ML, Neural Networks & Real-World Applications

By the end of this module you will be able to apply scikit-learn for common ML tasks, build a basic neural network with PyTorch, and implement robust ML pipelines including data preprocessing, proper train/test splits, cross-validation, and model evaluation on real-world datasets.

6 videos
3 readings
6 topics
1 homework
Learn
01

Learn

Watch curated videos and read study resources

02

Practice

Practice what you learned

03

Build Projects

Build projects using your new gained knowledge

04

Submit & Verify

Submit your project and get verified by our system

Rate this roadmap

0.0
0 reviews

Help the community find verified technical paths.

Community Insights

0

Join the discussion

Sign in to share your thoughts and technical insights.

Loading insights...