The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for the purpose of dimensionality reduction.
-
Updated
Nov 11, 2020 - Jupyter Notebook
The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for the purpose of dimensionality reduction.
Create a few popular Neural Networks from scratch using just Numpy
speech-enhancement-flask
This work applies autoencoder to denoise the image in the "cifar10" dataset.
Deep learning & neural network applications
BlurRemoval-Using-an-Autoencoder Are you poor at taking photos Just like me? Here I have made a Deep learning model using Autoencoder architecture to remove unwanted blur from the image.
All the models of Autoencoders that I've worked on
The official implemenataion of the "Denoising Architecture for Unsupervised Anomaly Detection in Time-Series" paper.
Heavy-Tailed distributions in Variational Autoencoder (VAE)
PyTorch implementations of an Undercomplete Autoencoder and a Denoising Autoencoder that learns a lower dimensional latent space representation of images from the MNIST dataset.
Autoencoder which will remove the noise from images. For training we need dataset with noise and dataset without nois, we dont havemnist data with noise so first we will add some gaussian noise into the whole mnist data.
Experimental Adversarial Attack notebooks on CV models
PyTorch implementation of a modified Denoising Autoencoder for improved imputation performance (Bachelor Thesis Project)
Semester 8 (Jan 2023 - May 2023)
The standard approach to image reconstruction using deep learning is to use clean image priors for training purposes. In this project, we attempt to achieve denoising without using a clean image prior and yet, achieving a performance comparable to, or sometimes, even better than that obtained using the conventional approach.
Various techniques are compared for retrieving an image from existing dataset which is similar to the test image.
A tutorial of Denoising Autoencoder which removes noise from MNIST images.
Add a description, image, and links to the denoising-autoencoders topic page so that developers can more easily learn about it.
To associate your repository with the denoising-autoencoders topic, visit your repo's landing page and select "manage topics."