SSL (self supervised learning) experiments for machine learning topics course
-
Updated
May 26, 2024 - Jupyter Notebook
SSL (self supervised learning) experiments for machine learning topics course
Graph-induced Syntactic-Semantic Spaces in Transformer-based VAE
Solutions for Advanced Image Analysis course assignments, featuring model designs for image summation and generation with MNIST, and style transfer using CycleGAN with MNIST and SVHN datasets.
Some mini-projects using well known datasets to practice important deep learning concepts.
Variational Autoencoders. This implements and pokes the original VAE in < 100 lines.
Recommender system for songs using different neural networks: MLP, VAE and flow
Testing the Reproducibility of the paper: MixSeq. Under the assumption that macroscopic time series follow a mixture distribution, they hypothesise that lower variance of constituting latent mixture components could improve the estimation of macroscopic time series.
Variational Autoencoder with PyTorch
A repository for generating synthetic data (images) using various DL/ML models.
A variational Autoencoder (VAE) to generate human faces based on the CelebA dataset. A VAE is a generative model that learns to represent high-dimensional data (like images) in a lower-dimensional latent space, and then generates new data from this space.
Genarating new MNIST images using VAE's
📜 [MIDL 2022] "Sensor to Image Heterogeneous Domain Adaptation Network", Ishikaa Lunawat, Vignesh S, S P Sharan
Research Project in A3C reinforcement learning algorithm used for path finding mobile robots
Code for Bachelor Thesis "Unveiling Hidden Features: Multimodal Integration Using Cross-Modal Variational Autoencoders for the Identification of Stratification in ABIDE"
Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders
Add a description, image, and links to the vae-pytorch topic page so that developers can more easily learn about it.
To associate your repository with the vae-pytorch topic, visit your repo's landing page and select "manage topics."