Skip to content

Files

Latest commit

 

History

History
57 lines (36 loc) · 3.14 KB

machine-learning-and-fundamentals-of-ai.md

File metadata and controls

57 lines (36 loc) · 3.14 KB

📈 Machine Learning and Fundamentals of AI

📅 Expected Duration: 8 weeks

This section contains the necessary material to introduce you to Machine Learning and the concepts fundamental to all AI systems. Completing this course will give you the foundational knowledge of Machine Learning and its applications, enabling you to understand core AI principles, develop intelligent systems, and solve real-world problems. It will also lay the groundwork for deeper exploration into areas like Deep Learning and Natural Language Processing.

By the end of this section, you will be able to:

  1. Preprocess and analyze datasets
  2. Understand and implement key ML algorithms
  3. Train, evaluate, and optimize ML models
  4. Interpret model performance using key metrics
  5. Work with Kaggle datasets and notebooks effectively

📌 Tasks

  1. CyberML(https://amritauniv.sharepoint.com/sites/CyberML)
    This course builds your foundational understanding of machine learning concepts, metrics, and training pipelines that are essential before diving into deep learning. Watch all lectures and complete the labs up to Week 11.\

  2. Kaggle Notebooks
    Explore the top Kaggle notebooks for ML models to understand how machine-learning algorithms are applied in different scenarios. Focus on key aspects such as Feature engineering, Exploratory Data Analysis (EDA), Model training and evaluation. After going through some of the notebooks, you should be able to take a dataset, preprocess it and train an appropriate model on it. You can use some of the notebooks and datasets given below for learning and as reference:

    Datasets:

    Spaceship Titanic Dataset: Link (Binary classification)

    Obesity classification Dataset: Link (Multi-class classification)

    House Prices Dataset: Link (Regression)
    \

    Notebooks:

    Spaceship Titanic: Link

    Obesity Classification: Link

    House Price: Link



    Start this in parallel with the CyberML course after completing content up to Week 5.

Additional Reading material


Extra reading material that students can go through to get a better understanding of the underlying math for most ML models.

  1. Linear Algebra: Link
  2. Calculus: Link
  3. Probability: Link
  4. Gradient Descent: Link
  5. Linear Regression: Link
  6. In-depth math and implementation of ML algorithms from scratch: Link