criso123/machine-learning-course

Follow the "Welcome to Machine Learning" course from Coursera teached by Andrew Ng

machine-learning-course

Following the "Welcome to Machine Learning" course from Coursera teached by Andrew Ng

1. Linear Regression

    1.1. Compute cost function 
    1.2. Gradient Descent 
    1.3. Cost function for multiple variables
    1.4. Gradient Descent for multiple variables
    1.5. Normalize features
    1.6. Normal equations  
   

2. Logistic Regression and regularization

    2.1. Sigmoid Function
    2.2. Logistic Regression Cost Function
    2.3. Logistic Regression Prediction Function
    2.4. Regularized Logistic Regression Cost
   

3. Multi-class classification and Neural Networks

    3.1. Logistic Regression cost function
    3.2. Train a one-vs-all multi-class classifier
    3.3. Predict using a one-vs-all multi-class classifier
    3.4. Neural network prediction function
   

4. Neural networks Learning

    4.1. Compute the gradient of the sigmoid function
    4.2. Randomly initialize weights
    4.3. Neural network cost function
   

5. Regularized Linear Regression and Bias v.s. Variance

    5.1. Regularized linear regression cost function
    5.2. Maps data into polynomial feature space
    5.3. Generates a cross validation curve
   

6. Support Vector Machine

    6.1. Gaussian Kernel for SVM
    6.2. Email preprocessing
    6.3. Feature extraction from emails
   

7. K-means Clustering and Principal Component Analysis

    7.1. Perform principal component analysis
    7.2. Projects a data set into a lower dimensional space
    7.3. Recovers the original data from the projection
    7.4. Find and compute closest centroids
    7.5. Initialization for K-means centroids
   

8. Anomaly Detection and Recommender Systems

    8.1. Estimate the parameters of a Gaussian distribution with a diagonal covariance matrix
    8.2. Find a threshold for anomaly detection
    8.3. Implement the cost function for collaborative filtering