This is a short post aiming to provide some accessible context into the concept of MoEs, not a fully comprehensive or technical look into the technology. See the last section for further reading. That being said, please do reach out if you see any issues with this or any other posts. Prefer to listen? Your browser does not support the audio element. Download and listen to the audio file here!

Understanding Neural Networks with Iris Dataset Today we will specifically look at implementing solutions to classification problems. A classification problem is where we are trying to categorise our input into two or more discrete categories. For example we could be categorising hand drawn numbers, that’s A-Z, a-z, 0-9 - This would be a multiclass classification problem with 62 classes. On the other hand, if we are classifying between malignant skin marks vs benign - this would be a binary classification problem.

An Introduction to PWN Challenges PWN challenges are a type of CTF challenge that require you to exploit a binary typically running on a remote server. This can be done by exploiting a vulnerability in the binary, or by using a vulnerability in the binary to gain access to the system. Often, PWN challenges will require you to gain access to a remote server, and then exploit the binary on that server.