Exercises of my CST Part III Probabilistic Machine Learning (LE49) module

Code for "SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation" @ ICML 2022

Generate classical paintings using Variational Autoencoders (VAEs).

VARIATIONAL AUTOENCODERS are Generative model. A Generative Model is a powerful way of learning any kind of data distribution using unsupervised learning and it has achieved tremendous success over the past few years.

Algorithms for inference in Gaussian Mixture Models.

VAE(Variational AutoEncoder) Recsys example using tensorflow

Personal implementation of a simple VAE in PyTorch as described in "Auto-Encoding Variational Bayes" [Kingma, Welling, 2014]

Unofficial PyTorch implementation of GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

TensorFlow code and LaTex for Bachelor Thesis: Understanding Variational Autoencoders' Latent Representations of Remote Sensing Images 🌍

Implementation of "Auto-Encoding Variational Bayes" by Kingma and Welling, 2014 in Julia [VAE in Julia]. Still working on it.

Use a VAE to generate all new pokemons

A Tensorflow-layer API Implementation of Deep Generative Models (MNIST Examples)

A variational autoencoder node for factor-graphs.

The study relied on conditional Variational Autoencoders to generate x-ray images, so that we can be able to regenerate the images according to the most important information that the x-ray images can contain (important information extraction).

The project explores a range of methods, including both statistical analysis, traditional machine learning and deep learning approaches to anomaly detection a critical aspect of data science and machine learning, with a specific application to the detection of credit card fraud detection and prevention.

🌟 Welcome to the Machine Learning and Deep Learning Projects repository! This project is a compilation of diverse and engaging projects spanning computer vision, Kaggle competitions, generative AI, and advanced techniques such as autoencoders and variational autoencoders

Smooth Variational Graph Embeddings for Efficient Neural Architecture Search

Using VAEs and GANs to understand how to generate images, over the CelebA dataset

Implementation of different approaches to train Discrete Variational Autoencoders

Investigative project for my CST Part III Probabilistic Machine Learning (LE49) module