Published onNovember 9, 2023Monotonic AttentionmlspeechWrite-up explaining my implementation of monotonic attention using a probabilistic graphical model.
Published onSeptember 16, 2023Retentive Networks and RWKVmlnlpA short, hand-wavy explainer for the mathematical intuition behind faster attention mechanisms.
Published onSeptember 14, 2023Miscellaneous Azure NotesreferencesMiscellaneous notes about various Azure-related things.
Published onSeptember 13, 2023Miscellaneous AWS NotesreferencesMiscellaneous notes about various AWS-related things.
Published onAugust 24, 2023Streaming ConvolutionsmlspeechWorking out the math for streaming convolutions.