my solutions to Coursera Machine Learning course, using python

• ex1 - Linear Regression

  • ex1-oneVariable.ipynb : Linear regression (one variable), gradient descent and scikit learn
  • ex1-multipleVariables.ipynb : Linear regression (multiple variable), gradient descent and scikit learn

• ex2 - Logistic Regression

  • ex2.ipynb : Two parts: Not regularized, Regularized (polynomial features), logistic regression using scikit learn is practiced in assignment 3

• ex3 - Logistic Regression and Neural Networks

  • ex3-logistic.ipynb : Multi-Class logistic regression (mnist dataset), using gradient descent (Method 1) and scikit learn (Method 2)
  • ex3-neural.ipynb : Implementation of forward-propagation in order to find training accuracy of a given neural network

• ex4 - Neural Networks

  • ex4.ipynb : A NeuralNetwork class, generalized to whatever network architecture user wants, using fmin_cg to minimize cost function

• ex5 - Regularized Linear Regression and Bias vs. Variance

  • ex5.ipynb : Linear regression with regularization, learning curves, polynomial linear regression with plots and finding best lambda for our regularization.