← All topics
Deep Learning
Neural networks from perceptrons to transformers.
Editorial articles
Suresh Madhra · Jun 11, 2026
Transformers, Explained Without the Hype
Self-attention, positional encodings and the residual stream — a mental model that survives contact with real code.
Suresh Madhra · May 15, 2026
The Only Loss Function Cheat Sheet You Need
MSE, MAE, Huber, quantile, cross-entropy, focal and contrastive — what each optimises, when it is the right call, and what it does badly.
From the community
Write for this topic →No community articles in this topic yet.