Mo Kleit's repositories
sim2real-cycleGAN
We train a CycleGAN model that will generate "realistic" augmented images based on images coming from the Duckietown simulator. This is in an attempt to reducing the reality gap when transitioning from robot training in simulation to real life.
course-extra
Extra modules
data-structures-algorithms-ift2015
Repository for all homeworks in ift2015. Includes Java implementations for LinkedList, Huffman Code and Bloom Filter.
generative-discriminative-classifier
Paper exploring comparison between generative and discriminative classifiers
multi-layer-perceptron
Implementation of an MLP
social-media-prediction
This is a Kaggle competition as part of the Data Science course at the MILA (IFT6758). We will try to predict the number of likes on social media.
text-classification-naive-bayes-implementation
This repository presents the implementation from scratch (using python and numpy only) of Naive Bayes classifier for text classification in the context of a Kaggle competition.
text-classification-scikit
This repository presents the implementation of different classifiers using sci-kit for a text classification competition in Kaggle.
topic-modeling-lda
We explore and implement LDA in order to estimate topics on various datasets (text documents).
speechbrain
A PyTorch-based Speech Toolkit