Contains Solutions and Notes for the Machine Learning Specialization by Andrew NG on Coursera

Note : If you would like to have a deeper understanding of the concepts by understanding all the math required, have a look at Mathematics for Machine Learning and Data Science

• Week 1

  • Practice quiz: Regression
  • Practice quiz: Supervised vs unsupervised learning
  • Practice quiz: Train the model with gradient descent
  • Optional Labs
    • Model Representation
    • Cost Function
    • Gradient Descent

• Week 2

  • Practice quiz: Gradient descent in practice
  • Practice quiz: Multiple linear regression
  • Optional Labs
    • Numpy Vectorization
    • Multi Variate Regression
    • Feature Scaling
    • Feature Engineering
    • Sklearn Gradient Descent
    • Sklearn Normal Method
  • Programming Assignment
    • Linear Regression

• Week 3

  • Practice quiz: Cost function for logistic regression
  • Practice quiz: Gradient descent for logistic regression
  • Optional Labs
    • Classification
    • Sigmoid Function
    • Decision Boundary
    • Logistic Loss
    • Cost Function
    • Gradient Descent
    • Scikit Learn - Logistic Regression
    • Overfitting
    • Regularization
  • Programming Assignment
    • Logistic Regression

• Week 1

  • Practice quiz: Neural networks intuition
  • Practice quiz: Neural network model
  • Practice quiz: TensorFlow implementation
  • Practice quiz : Neural Networks Implementation in Numpy
  • Optional Labs
    • Neurons and Layers
    • Coffee Roasting
    • Coffee Roasting Using Numpy
  • Programming Assignment
    • Neural Networks for Binary Classification
  
  

• Week 2

  • Practice quiz : Neural Networks Training
  • Practice quiz : Activation Functions
  • Practice quiz : Multiclass Classification
  • Practice quiz : Additional Neural Networks Concepts
  • Optional Labs
    • RElu
    • Softmax
    • Multiclass Classification
  • Programming Assignment
    • Neural Networks For Handwritten Digit Recognition - Multiclass

• Week 3
  • Practice quiz : Advice for Applying Machine Learning
  • Practice quiz : Bias and Variance
  • Practice quiz : Machine Learning Development Process
  • Programming Assignment
    • Advice for Applied Machine Learning

• Week 4
  • Practice quiz : Decision Trees
  • Practice quiz : Decision Trees Learning
  • Practice quiz : Decision Trees Ensembles
  • Programming Assignment
    • Decision Trees

• Week 1
  • Practice quiz : Clustering
  • Practice quiz : Anomaly Detection
  • Programming Assignments
    • K means
    • Anomaly Detection

• Week 2
  • Practice quiz : Collaborative Filtering
  • Practice quiz : Recommender systems implementation
  • Practice quiz : Content-based filtering
  • Programming Assignments
    • Collaborative Filtering RecSys
    • RecSys using Neural Networks

• Week 3
  • Practice quiz : Reinforcement learning introduction
  • Practice Quiz : State-action value function
  • Practice Quiz : Continuous state spaces
  • Programming Assignment
    • Deep Q-Learning - Lunar Lander

This Course is a best place towards becoming a Machine Learning Engineer. Even if you're an expert, many algorithms are covered in depth such as decision trees which may help in further improvement of skills.

Special thanks to Professor Andrew Ng for structuring and tailoring this Course.

• Write an unsupervised learning algorithm to Land the Lunar Lander Using Deep Q-Learning

  • The Rover was trained to land correctly on the surface, correctly between the flags as indicators after many unsuccessful attempts in learning how to do it.
  • The final landing after training the agent using appropriate parameters :

• Write an algorithm for a Movie Recommender System

  • A movie database is collected based on its genre.
  • A content based filtering and collaborative filtering algorithm is trained and the movie recommender system is implemented.
  • It gives movie recommendentations based on the movie genre.

• And Much More !!

Concluding, this is a course which I would recommend everyone to take. Not just because you learn many new stuffs, but also the assignments are real life examples which are exciting to complete.

Happy Learning :))