Welcome to the 4th issue of the Papers with Code newsletter. Self-attention continues to be adopted to build deep learning architectures that address computer vision problems like instance segmentation and object detection. One recent example is Vision Transformer (ViT) proposed by Dosovitskiy et al. Despite being promising for vision tasks, these large models can show computational inefficiencies and inferior performance (compared to established vision architectures). This leaves room for improvements.

Transformers have accelerated the development of new techniques and models for natural language processing (NLP) tasks. While it has mostly been used for NLP tasks, it is now seeing heavy adoption to address computer vision tasks. That makes it a very important technique to understand and be able to apply. I am aware that a lot of machine learning and NLP students and practitioners are keen on learning about transformers. Therefore, I am motivated to prepare and maintain a recipe of resources and study materials to help students learn about the world of Transformers.

It is useful, for the forthcoming discussion, to have a better understanding of some key terms used in RL. Agent: A software/hardware mechanism which takes certain action depending on its interaction with the surrounding environment; for example, a drone making a delivery, or Super Mario navigating a video game. The algorithm is the agent. Action: An action is one of all the possible moves the agent can make. An action is almost self-explanatory, but it should be noted that agents usually choose from a list of discrete possible actions.