Explore projects
-
Machine learning techniques to classify water samples as drinkable or not drinkable.
Updated -
FakET: Simulating Cryo-Electron Tomograms with Neural Style Transfer
Updated -
Lyric to musical melody generation task
Updated -
UBC Seagull / DoujinCI
GNU Affero General Public License v3.0Automated pipeline for decensoring of doujinshis, using HentAI and DeepCreamPy. Supply an Imgur album link, nhentai link or nhentai id, wait 15-30 minutes, and download significantly decensored images.
Updated -
This learning project uses a neural network to predict the winner of a League of Legends game after 10 minutes ingame given the current data. The main branches notebook has an accuracy of roughly 58.5%, while the NN with manually added weights has one of roughly 66.9% but has problems with the validation accuracy and loss.
Updated -
mlrep / mldev
Apache License 2.0$ mldev | is a data science experiment automation and reproducibility toolkit.
check our experiment templates: https://gitlab.com/mlrep
Updated -
ComputationalScience / ABM Control
MIT LicenseThis projects implements neural-network controllers for two agent-based models: (i) a predator-prey model and (ii) a metabolic network model.
Updated -
-
-
A project focused on weather classification using advanced deep learning techniques, specifically leveraging TensorFlow and a custom Convolutional Neural Network (CNN). The project involved the integration of four diverse weather datasets, namely ACDC, MWD, UAVid, and Syndrone, covering various weather conditions, including clear sky, cloudy, rainy, and sunny weather. Developed a custom CNN architecture using TensorFlow's Keras API, incorporating convolutional layers for feature extraction and dense layers for classification.
Updated -
Armand Rousselot / quantumML
MIT LicenseA project that introduces a Quantum Invertible Neural Network (QINN). The invertible architecture can be trained as a density estimator to perform data generation. Implemented using Pennylane.
Updated -
Evaluation of various Machine learning models for sentiment analysis You are given the reviews dataset. These are 194439 amazon reviews for cell phones and accessories taken from https://jmcauley.ucsd.edu/data/amazon/ Use the “reviewText” and “overall” fields from this file. The goal is to predict the rating given the review by modeling it as a multi-class classification problem. • Take the first 70% dataset for train, next 10% for validation/development, and remaining 20% for test. • Traditional machine learning methods • Design some good linguistic features. You can start with basic TFIDF features. Use these classifiers: J48 decision trees, SVMs with linear/RBF kernel, logistic regression, xgboost, random forests and report accuracy on test set.
Updated -
[Python] The project focuses on parallelizing the sequential implementation of K nearest neighbors (kNN) algorithm - a basic supervised learning algorithm in Machine Learning, together with evaluating its performance based on some benchmark metrics.
Updated -
The goal of the project is to build a workflow for modeling topics from youtube video transcript in the context of the Tournesol project : https://tournesol.app/
Updated -
A library of blog posts and tutorials. Part of the End-to-End Machine Learning School at e2eml.school/courses
Updated -
Collection of completed data-mining (university course) on python
Updated -
picos-api / Workshop Berlin 2023
Creative Commons Attribution 4.0 InternationalWorkshop held in the Summer School on Optimization and Machine Learning at ZIB in Berlin, 2023.
Updated -
Nous avons entrepris un projet d'apprentissage automatique pour prédire des maladies en analysant les données symptomatiques et médicales. Notre modèle sophistiqué, basé sur des techniques d'apprentissage automatique avancées, évalue les symptômes pour fournir des prédictions précises. Avec une interface API développée avec Django et un déploiement sur Microsoft Azure via Terraform, notre solution est conviviale et évolutive.Découvrez notre projet ici :https://apipharma-app-service.azurewebsites.net/
Updated