Latent Space

Just some late-night thoughts on inference, deep learning, LLMs, and building intelligent systems.

Hyperparameter Tuning: Finding the Sweet Spot

Training deep learning models is a bit like tuning a car, you've got a bunch of knobs to adjust, and finding the sweet spot takes patience and know-how.

Effect of learning rate on loss

Gelator Transparency Classification using Kernel Ridge Regression

Applying kernel ridge regression to perform binary classification on the transparency of anionic/cationic gelators under different experimental conditions (sparse data regime).

Chemical structure variations