AI Learning Roadmap

2026 Edition

A 16-week structured plan to go from complete beginner to job-ready AI practitioner. Curated by MAXimuz Learn.

100% Free ResourcesProject-BasedIndustry-Aligned

Phase 1

Getting Started

Week 1-2

Prerequisites

Basic Python programming

High school mathematics

Curiosity & consistency

Week 1: Python for Data Science

NumPy basics
Pandas for data manipulation
Matplotlib for visualization

Week 2: Mathematics Refresher

Linear algebra essentials
Basic statistics & probability
Calculus concepts (derivatives)

Phase 2

Core Machine Learning

Week 3-6

Week 3-4: Supervised Learning

Linear & logistic regression
Decision trees & random forests
Support vector machines
Model evaluation metrics

Week 5-6: Unsupervised Learning

K-means clustering
Principal component analysis
Dimensionality reduction

⭐ Recommended Course

Machine Learning Specialization by Andrew Ng

Stanford University / Coursera • The gold standard for ML education

Phase 3

Deep Learning Foundations

Week 7-10

Week 7-8: Neural Networks

Perceptrons & activation functions
Backpropagation
Optimization algorithms

Week 9-10: CNNs

Image classification
Object detection basics
Transfer learning

⭐ Recommended Resources

• 3Blue1Brown Neural Networks Series (YouTube) - Best visual explanations
• fast.ai Practical Deep Learning for Coders - Top-down approach

Phase 4

Choose Your Specialization

Week 11-16

Pick ONE path based on your interests and career goals:

Path A

Natural Language Processing

Transformers & attention
BERT, GPT architecture
Prompt engineering
Building with LLM APIs

Path B

Computer Vision

Advanced CNN architectures
Object detection (YOLO)
Image segmentation
Video analysis

Path C

Robotics & Embodied AI

Robot Operating System
Motion planning
Sensor fusion
Reinforcement learning

Practical Projects

Build your portfolio alongside learning

Beginner

Sentiment analysis classifier
Image classification app
Simple chatbot

Intermediate

Object detection system
Recommendation engine
Time series forecasting

Advanced

Fine-tune an LLM
Build a RAG application
Multi-modal AI system

Top Free Resources

Quality over quantity - our best picks

📚 Courses

1. Stanford CS229: Machine Learning
2. MIT 6.S191: Introduction to Deep Learning
3. Google ML Crash Course
4. fast.ai Practical Deep Learning

📖 Books (Free Online)

1. Deep Learning Book (Goodfellow et al.)
2. The Elements of Statistical Learning
3. Neural Networks and Deep Learning

🎬 YouTube Channels

1. 3Blue1Brown - Visual explanations
2. StatQuest - Statistics made clear
3. Andrej Karpathy - From the expert

💻 Practice Platforms

1. Kaggle - Competitions & datasets
2. Google Colab - Free GPU access
3. Hugging Face - Models & datasets

Start Your Journey Today

Visit learn.maximuz.tech for more curated resources