- KD-trees: Classification of n points in d-sized Euclidean space
This is a little writeup of a project I did in collaboration with a classmate while studying a algorithmic complexity class. We implemented a faster, but still exact, $k$ nearest neighbors classifier based on k-d trees. I learned a lot and hope this can be interesting to some of you.Read More
- Adanet - adaptive network structures
The goal of this project is to reproduce the methods and experiments of the following paper:Read More
C. Cortes, X. Gonzalvo, V. Kuznetsov, M. Mohri, S. Yang AdaNet: Adaptive Structural Learning of Artificial Neural Networks. We will try to reproduce their method that consists in building neural networks whose structure is learned and optimized at the same time as it’s weights.This method will be applied to a binary classification task on images from the CIFAR-10 dataset.