Time-Series Forecasting: Classical Methods vs. Neural Approaches
When ARIMA and exponential smoothing still beat a neural forecaster, and when the added complexity of a deep learning model actually pays off.
Tag
5 articles
When ARIMA and exponential smoothing still beat a neural forecaster, and when the added complexity of a deep learning model actually pays off.
A conceptual walkthrough of what attention mechanisms actually do, working up from the original translation problem they were built to solve.
What embeddings actually are, why distance in that space means something, and how to reason about them without wading through linear algebra.
A practical guide to spotting overfitting early and choosing the right regularization technique for the model family you're actually using.
A practical walkthrough of self-attention, multi-head attention, and positional encoding for engineers who need to reason about transformers, not just use them.