Machine Learning

Curriculum

1. Week 1

   Introduction to Machine Learning

   ML fundamentals, types of ML, core ML concepts and understanding how machine learning models work.

2. Data Preprocessing

   Data preprocessing techniques, preparing real-world datasets and creating clean data pipelines for machine learning.

3. Supervised Learning

   Supervised learning, classification, regression and training and evaluating ML models.

4. Week 2

   Unsupervised Learning

   Unsupervised learning, clustering, pattern discovery and K-Means clustering.

5. Advanced Machine Learning

   Advanced ML concepts, core ML algorithms and building complete end-to-end ML pipelines.

6. Week 3

   Natural Language Processing

   NLP, text processing, sentiment analysis, text classification and spam detection.

7. Computer Vision

   Computer vision applications, image classification and human activity recognition using sensor data.

8. Week 4

   Reinforcement Learning

   Reinforcement learning concepts, learning through interaction and rewards.

9. Model Deployment & Productionization

   Training ML models, model evaluation, end-to-end ML pipelines, deployment and productionization.

What you walk away with

• Build and evaluate machine learning models using real-world datasets
• Develop practical ML solutions across NLP, computer vision and core ML domains
• Train, deploy and productionize an end-to-end machine learning pipeline