Writing
DraftRead the draft →
Deriving the Prior-Data Fitted Network
From Bayesian prediction to tabular in-context learning, Do-PFN, and time-series forecasting. With figures you can move.
Notes
DraftRead the note →
Transformers as memory: the mathematics, from matrices to a unified view
Matrix-vector and matrix-matrix views, outer-product memories, the MLP as slow memory, attention as a soft dictionary, fast and slow weights, and one unified table, with twenty-two interactive figures.