Underlining Mathematics of a Machine Learning Algorithm is the most important thing we need to know while learning it. And the best way to learn it is by implementing it from scratch using only built-in python libraries such as numpy. So in this repository, I will be implementing most of the common Machine Learning algorithms that we use from scratch without using sklearn etc.
- K- Nearest Neighbors (KNN) - KNN Implementation from Scratch
- Linear Regression - Linear Regression from Scratch
- Logistic Regression
- Support Vector Machines (SVM)
- Decision Trees
- K-Means Clustering
- Naive Bayes
- Random Forest
- Neural Networks
Steps I will follow for each Algorithms -
- Write a brief introduction of each Algorithm in Readme file along with its Mathematical Intuition
- Implement Machine Learning Algorithm from scratch using python & Numpy only (.py file)
- Pick a dataset for a real world use case and train the above implemented algorithm on it
- Compare the metrics(Accuracy, f1 score, MSE etc) we get from above implementation with the Sklearn implementation