ZARZA We are Zarza, the prestigious firm behind major projects in information technology.
Listen "4: Can Neural Nets Learn the Same Model Twice?"
Episode Synopsis
Todays paper: Can Neural Nets Learn the Same Model Twice? Investigating Reproducibilityand Double Descent from the Decision Boundary Perspective (https://arxiv.org/pdf/2203.08124.pdf)Summary:A discussion of reproducibility and double descent through visualizations of decision boundaries.Highlights of the discussion:Relationship between model performance and reproducibilityWhich models are robust and reproducibleHow they calculate the various scores
More episodes of the podcast Argmax
Mixture of Experts
08/10/2024
LoRA
02/09/2023
15: InstructGPT
28/03/2023
14: Whisper
17/03/2023
13: AlphaTensor
10/03/2023
12: SIRENs
24/10/2022
9: Heads-Up Limit Hold'em Poker Is Solved
29/07/2022
8: GATO (A Generalist Agent)
29/07/2022
In God we trust