autoencoder

Understand Autoencoders by implementing in TensorFlow

Autoencoders are a type of unsupervised neural networks and has two components: encoder and decoder. We have provided the intuitive explanation of the working of autoencoder along with a step by step TensorFlow implementation.

Machine Learning (ML)

Converting colored images (RGB) to grayscale using Autoencoder

We built an autoencoder from scratch in TensorFlow to generate the grayscale images from colored images.

Machine Learning (ML)

Generate new MNIST digits using Autoencoder

In this article, we will learn how autoencoders can be used to generate the popular MNIST dataset and we can use the result to enhance the original dataset.

Machine Learning (ML)

Build and use an Image Denoising Autoencoder model in Keras

In this article, we will see How encoder and decoder part of autoencoder are reverse of each other? and How can we remove noise from image, i.e. Image denoising, using autoencoder? in Keras

Machine Learning (ML)

Applications of Autoencoders

Autoencoders are neural networks that aim to copy their inputs to outputs. The applications of autoencoders are Dimensionality Reduction, Image Compression, Image Denoising, Feature Extraction, Image generation, Sequence to sequence prediction and Recommendation system.

Machine Learning (ML)

Different types of Autoencoders

Autoencoder is an artificial neural network used to learn efficient data codings in an unsupervised manner. There are 7 types of autoencoders, namely, Denoising autoencoder, Sparse Autoencoder, Deep Autoencoder, Contractive Autoencoder, Undercomplete, Convolutional and Variational Autoencoder.

Machine Learning (ML)

An autoencoder is a neural network that learns data representations in an unsupervised manner. Its structure consists of Encoder, which learn the compact representation of input data, and Decoder, which decompresses it to reconstruct the input data.