Articles & Writings
Technical essays, theoretical derivations, and computational notes written by Chima Emmanuel.
9 min read
Autoencoders and Representation Learning in Vision
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.
#Machine Learning#Computer Vision#Mathematics#Medical Imaging
Read article5 min read
The Weird Geometry of High-Dimensional Representations: Why Your ML Models Behave Differently
In high dimensions, our geometric intuition fails. All points become equidistant, random vectors become orthogonal, and the very concept of a nearest neighbor collapses.
#Machine Learning#Geometry#Mathematics#Vector Spaces
Read article9 min read
Why Neural Networks Fail on Constraints and why Lagrangian Geometry works better
Exploring why standard neural networks struggle with strict constraints and how Lagrangian geometry provides a more principled approach to obedience rather than approximation.
#Machine Learning#Mathematics#Optimization#Neural Networks
Read article