Claude COULOMBE's Projects
Jupyter notebook running through some basic examples of Distributed TensorFlow
EASE (Enhanced AI Scoring Engine) is a library that allows for machine learning based classification of textual content. This is useful for tasks such as scoring student essays.
EcorcIA, une application mobile pour téléphone intelligent Android réalisé dans le cadre du cours VIARENA
EcorcIA Web, un serveur d'inférences en ligne, avec TensorFlow Serving, Docker et Flask
Notebooks explaining the intuition behind the Expectation Maximisation algorithm
Accompanying notebook for the Entailment with Tensorflow article.
Petit exercice IPython d'exploration, de visualisation et de prédiction simple de l'évolution temporelle de la pandémie du COVID-19. ---------------- Small exercise of data exploration, visualization and prediction of the evolution over time of the COVID-19 pandemic.
Minimum viable experiments using Reinforcement Learning QLearning and evolution strategy to play catch - by Eder Santana http://edersantana.github.io - Small corrections and addition of iPython Notebooks by Claude COULOMBE - PhD candidate - TÉLUQ / UQAM - Montréal
This repository contains the full code for the "Towards fairness in machine learning with adversarial networks" blog post.
The fast.ai deep learning library, lessons, and tutorials
A French Lemmatizer in Python based on the LEFFF
A repository that contains companion Python code and comments to the GBC (Goodfellow, Bengio, Courville) Deep Learning Book. And a blog post on Medium.com:
Deep learning applied to georeferenced datasets
Code for the paper "Language Models are Unsupervised Multitask Learners"
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
Python Module for decision tree based hierarchical multi-classification
JPPT-0: Je n'ai Pas PéTé mon budget calcul! Génération de textes à zéro dollar de calcul... - Un petit générateur de textes en français basé sur un modèle de langue (i.e. un modèle de prédiction du prochain mot) à base de ngrammes et d'une chaîne de Markov.
2nd place solution to the Kaggle Right Whale challenge
Deep Learning for humans
Provides a SpatialDataGenerator class for accessing spatial data.
Keras library for building (Universal) Transformers, facilitating BERT and GPT models
CNN based autoencoder combined with kernel density estimation for colour image anomaly detection / novelty detection. Built using Tensforflow 2.0 and Keras
A Python implementation of LightFM, a hybrid recommendation algorithm.
Copie ds scripts de peaufinage de GML
LSTM language model with CNN over characters
How to build a Multilayered LSTM Network to infer Stock Market sentiment from social conversation using TensorFlow.
Materials for class on machine learning/deep learning using scikit-learn, tensorflow and keras
Misc code snippets for Jupyter/Cloud Datalab
Monte carlo tree search in python