My Articles

Autoencoders are a type of neural network that compress data into a lower-dimensional space and then reconstruct the original input from that compressed representation.

Exploring why standard neural networks struggle with strict constraints and how Lagrangian geometry provides a more principled approach to obedience rather than approximation.

In high dimensions, our geometric intuition fails. All points become equidistant, random vectors become orthogonal, and the very concept of a nearest neighbor collapses.