_index.org

meeting 7/25

Last edited: August 8, 2025

meeting 8/1

Last edited: August 8, 2025

Updates

Yay mend works!

.mean() vs. .sum() for the dW maps?

PPL Isn’t the Only Possible Metric

even if our model is better ppl, its worse at squad than Facebook (granted its been trained a lot less); will run with new pretraining model (expect that no dropout will be better (see paper above)).

Meghanani 2021

Last edited: August 8, 2025

DOI: 10.3389/fcomp.2021.624558

One-Liner

analyzed spontaneous speech transcripts (only!) from TD and AD patients with fastText and CNN; best was \(83.33\%\) acc.

Novelty

  • threw the NLP kitchen sink to transcripts
    • fastText
    • CNN (with vary n-gram kernel 2,3,4,5 sizes)

Notable Methods

  • embeddings seaded by GloVe
  • fastText are much faster, but CNN won out

Key Figs

the qual results

PAR (participant), INV (investigator)

Notes

Hey look a review of the field:

Mel Scale

Last edited: August 8, 2025

Human do not perceive frequency very well. The Mel scale is a scale from Hertz to what’s better perceived.

memory

Last edited: August 8, 2025

memory is an array of bytes

  • each byte has a unique index which is written in hexadecimal
  • a pointer stores addresses to memory