Network Science Notes 1: Random Network
The analysis of network science is basically based on graph theory. We use some quantitative measures to describe the structure of a network and analyze its properties.
Tutorial
Posts about Tutorial.
Network Science Notes 2: Random Network
Random networks are the simplest type of network. By studying random networks, I get to know what aspects of a network are important and how to measure them.
Network Science Notes 3: Scale-Free Network
Deviated from the random network, the scale-free network has a power-law degree distribution and seems to be more common in real-world networks. What's the intrinsic mechanism behind it?
Network Science Notes 4: Growing Network
In this note we generate a network by adding nodes and links one by one (The Barabási-Albert Model), this mechanism will help to explain hubs and degree distribution in real-world networks.
Entropy, KL Divergence and Cross Entropy
Cross entropy is a loss function used in classification problems. This post will introduce the definition and the intuition behind cross entropy.
How to Evaluate the Performance of ML Models
Maching learning basically have 2 tasks: regression and classification. This post will introduce how to evaluate the performance of ML models in these 2 tasks.