Technical Deep Learning Focused Articles

Convolutional Neural Networks (CNNs) are the fundamental building blocks of many deep learning applications. Everyday computer vision solutions to tasks such as image classification, object detection, pose estimation, depth estimation are solved through the implementation of carefully designed CNN architecture. Throughout my academic and professional career, I have found that it's vital to have an in-depth awareness of the internal components that are employed to develop widely used CNN architecture. Transfer Learning and Fine Tuning have made access to state of the art CNN architecture easier. Nonetheless, it is beneficial to take a step back to the simplest architectures and earliest deep learning research papers and understand the initial building blocks of what we today observe as Deep Learning.