Implementation of a simple linear regression of training set using Gradient Descent algorithm and Normal Equations having single as well as multiple deciding features.
Implementation of a simple logistic regression of training set using Gradient Descent algorithm as well as inbuilt function fminunc having single as well as multiple deciding features. Implementation of regularization to reduce the variance of the algorithm results.
Implementing Multi Class Logistic regression algorithm to learn 20*20 pixel images of hand-written digits and analysing the same using given learned 3-layered Neural Network with proper regularization and analysing the percentage accuracy in both of them.
Implementing self learning Neural Network using the same example of 20*20 pixel hand-written digits.
Implementing Regularized Linear Regression to predict the amount of water flowing out of a dam using the change of water level in a reservoir and diagnostics of debugging learning algorithms and examining the effects of bias v.s. variance.
Implemented Email Spam Classifier using Support Vector Machines with linear as well as gaussian kernels.