Category: Deep Learning

When dealing with image data in deep learning, then convolutional neural networks (CNN) are the go-to architectures. Convolutional neural networks have proved to provide many state-of-the-art solutions and benchmarks in deep learning and computer vision. Image recognition, object detection, and semantic segmentation are only some of the applications of convolutional neural networks among many more. […] ...

In this tutorial, we will learn about sparse autoencoder neural networks using KL divergence. We will also implement sparse autoencoder neural networks using KL divergence with the PyTorch deep learning library. In the last tutorial, Sparse Autoencoders using L1 Regularization with PyTorch, we discussed sparse autoencoders using L1 regularization. We also learned how to code […] ...

In this article we explore Sparse autoencoders using L1 regularization using the PyTorch deep learning framework. ...

In this article, we will discuss how to get per-class accuracy in a highly imbalanced image/vision dataset. Deep learning algorithms suffer when the dataset is highly imbalanced. In image recognition, a deep neural network may predict 90% of one class correctly and only 20% of another class correctly. This is the result of the number […] ...

In this article, we train a ResNet34 deep neural network on the Caltech101 computer vision dataset. We use transfer learning and PyTorch deep learning library to achieve 95% test accuracy. ...