A collection of fundamental machine learning projects implementing Music Recommendation, Heart Disease Classification via SVM (including a custom solver), and various Regression techniques from scratch.

Convex Optimization and Polynomial System Solver with Dockerized Symbolic Computation via msolve, Sagemath & C++

Geometric operations on polytopes of any dimension

Vectorize the Matlab/CVX for-loops as much as possible.

Proposing a novel approach on using Naives Bayes by using Robust Kernel Density Estimation (RKDE) and optimising the bandwith(h) with Harris Hawks Optimization (HHO)

Desktop app for creating glaze recipes satisfying constraints on oxides and/or ingredients

SVM implementation from scratch in python.

Classification of a radially seperated dataset using SVM with RBF kernel using CVXOPT

The project Epsilon SVR is built from Scratch with minimum Sk Learn packages. This Epsilon SVR improves the SVR Model.

This code was written during the writing of my undergraduate thesis as a means to understand the inner details of Support Vector Machines. This includes a rough translation of the original \epsilon -SVR and \nu -SVR based on the C source code (https://www.csie.ntu.edu.tw/~cjlin/libsvm/))

Implement hard/soft margin SVM from scratch using numpy and cvxopt.

Solving Convex and Nonconvex Optimization Problems

Compilation of different ML algorithms implemented from scratch (and optimized extensively) for the courses COL774: Machine Learning (Spring 2020) & COL772: Natural Language Processing (Fall 2020)

Support Vector Machines from scratch using CVXOPT library.

Making HTML slides with Reveal.js and pandoc

Simple SVM

Custom implementation of Support Vector Machines using Python and NumPy