General

Resources

Based on Learn Machine Learning in 3 Months (PyTorch 🔥 Curriculum)

1. Mathematics of Machine Learning
   • Linear Algebra
   • Calculus
   • Statistics
   • Probability Theory
2. Kaggle
3. Machine Learning Techniques: iPython Cookbook
   • Supervised Learning
   • Unsupervised Learning
   • Reinforcement Learning
4. Dive into Deep Learning
   • Neural Networks
   • Optimization
   • Hardware

5. Transformers

   • Transformers
   • Attention
   • Transfer Learning

6. Diffusers

   • Generative Modeling
   • Interpretability
   • Multimodal Data
7. Deep Reinforcement Learning
   • RL Baselines
   • Unity
   • Q Learning
   • Proximal Policy Optimization
8. MLOps
9. Full-stack DL
   • CI Principles
   • Scaling Tools (PyTorchLightning, and w&b)
   • Deployment tools (Docker AWS, Lambda, Gradio & Streamlit)
10. Production
    • Containerization with Kubernetes
    • Monitoring web services
      • Prometheus
      • Evidently AI
      • Grafana Labs
      • MongoDB
      • Terraform
11. Data Engineering
    • Airflow and GCP for data ingestion
    • Kafka for streaming
    • Spark for batch processing

Useful modules for ML and Data Science

• Pandas - read and manipulate data
• Numpy - manipulating lists and tables of numerical data
  • Numba - makes Python code fast
• Matplotlib - for creating static, animated, and interactive visualizations in Python
• Scikit-learn - machine learning in Python
  • EDA - exploratory data analysis
  • Linear Regression
  • Logistic Regression
  • K-Nearest Neighbors
  • Decision Trees
  • Random Forest
  • Neural Networks
  • Clustering
  • Pipelines
  • Cross-Validation
  • Gradient Boosting
  • Data Leakage