Deep Learning
What can the history of supercomputing teach us about ARM-based deep learning architectures?
What does the NVIDIA's new ARM-based CPU chip mean for the future of deep learning? We take a look at this and other questions by looking at the history of high performance computing and how HPC architectures have been adopted within deep learning.
By
David
xUnit Spatial Activation Function for Image Denoising
This article provides an in-depth look at the CVPR 2018 paper titled "xUnit: Learning a Spatial Activation Function for Efficient Image Restoration" and its importance in the domain of image reconstruction.
Question Answering Models: A Comparison
This article covers a deeper level understanding of Question Answering models in NLP, the datasets commonly used, and how to choose a pre-trained model by considering various factors like the document structure, runtime cost, etc.
Concurrent Spatial and Channel Squeeze & Excitation (scSE) Nets
In this article, we will take a look at the paper "Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks" which serves as a design update for the popular Squeeze-and-Excitation attention module.
