CS231n-Deep-Learning-for-Computer-Vision

My attempt at the homework assignments of Stanford's CS231n class

Assignment 1

Goals

In this assignment you will practice putting together a simple image classification pipeline based on the k-Nearest Neighbor or the SVM/Softmax classifier. The goals of this assignment are as follows:

1. Understand the basic Image Classification pipeline and the data-driven approach (train/predict stages).
2. Understand the train/val/test splits and the use of validation data for hyperparameter tuning.
3. Develop proficiency in writing efficient vectorized code with numpy.
4. Implement and apply a k-Nearest Neighbor (kNN) classifier.
5. Implement and apply a Multiclass Support Vector Machine (SVM) classifier.
6. Implement and apply a Softmax classifier.
7. Implement and apply a Two layer neural network classifier.
8. Understand the differences and tradeoffs between these classifiers.
9. Get a basic understanding of performance improvements from using higher-level representations as opposed to raw pixels, e.g. color histograms, Histogram of Oriented Gradient (HOG) features, etc.