This repo contains the vanilla basic machine learning models built with just python and numpy. The goal is to:
- build a ML workflow and pipeline with data driven approach (train/predict stages)
- understand the train/val/test splits and the use of validation data for hyperparameter tuning
- develop proficiency in writing vectorized numpy codes
- implement basic machine learning models from scratch.
- Linear Regression
ML models with reference to CS231n: Convolutional Neural Networks for Visual Recognition
- KNN
- SVM
- Softmax
- Two Layer Neural Network
Download CIFAR 10 dataset Here