Deep Learning neural networks can work well for several tasks today. We can use deep neural networks for image recognition, object detection, segmentation, speech, NLP and much more. But there is one problem with deep neural networks. They are bad at handling noise during real-world testing. The generalization power of deep neural networks reduces drastically […] ...

Updated: March 25, 2020. In this post, we will be denoising text image documents using deep learning autoencoder neural network. And we will not be using MNIST, Fashion MNIST, or the CIFAR10 dataset. In fact, we will be using one of the past Kaggle competition data for this autoencoder deep learning project. More specifically, we […] ...

In this tutorial, you will learn how to make your own custom datasets and dataloaders in PyTorch. For this, we will be using the Dataset class of PyTorch. Introduction When carrying out any machine learning project, data is one of the most important aspects. Preparing, cleaning and preprocessing, and loading the data into a very […] ...

Updated: March 25, 2020. One of the applications of deep learning autoencoders is image reconstruction. But it is not necessary that the input images will always be clean. Sometimes, the input images for autoencoders can be noisy. In that case, the deep learning autoencoder has to denoise the input images, get the hidden code representation, […] ...

Updated: March 25, 2020. Convolutional autoencoders are some of the better know autoencoder architectures in the machine learning world. In this article, we will get hands-on experience with convolutional autoencoders. For implementation purposes, we will use the PyTorch deep learning library. What Will We Cover in this Article? Implementing convolutional autoencoders using PyTorch. Visualizing and […] ...