Introduction to Bilinear Interpolation.
This post introduce a new field of machine learning, i.e., meta learning, whose aim is to learn the “learn ability”. For example, we train a model on multiple learning tasks, such as speech recognition, image classification and so on, then when it perform a new task like text classification, it will learn faster and better since it has seen a lot of similar recognition tasks. In a nutshell, meta-learning algorithms produce a base network that is specifically designed for quick adaptation to new tasks using
Graph Convolutional Networks (GCNs) is one type of neural networks designed to work directly on graphs and leverage their structural information. In this post, I will introduce how information is propagated through the hidden layers of a GCN.