))
Deep Double Descent
Arkiveret serie ("Inaktivt feed" status)
When?
This feed was archived on February 21, 2025 21:08 (
Why? Inaktivt feed status. Vores servere kunne ikke hente et gyldigt podcast-feed i en længere periode.
What now? You might be able to find a more up-to-date version using the search function. This series will no longer be checked for updates. If you believe this to be in error, please check if the publisher's feed link below is valid and contact support to request the feed be restored or if you have any other concerns about this.
Manage episode 424087967 series 3498845
Indhold leveret af BlueDot Impact. Alt podcastindhold inklusive episoder, grafik og podcastbeskrivelser uploades og leveres direkte af BlueDot Impact eller deres podcastplatformspartner. Hvis du mener, at nogen bruger dit ophavsretligt beskyttede værk uden din tilladelse, kan du følge processen beskrevet her https://da.player.fm/legal.
We show that the double descent phenomenon occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with increasing model size, data size, or training time. This effect is often avoided through careful regularization. While this behavior appears to be fairly universal, we don’t yet fully understand why it happens, and view further study of this phenomenon as an important research direction.
Source:
https://openai.com/research/deep-double-descent
Narrated for AI Safety Fundamentals by Perrin Walker of TYPE III AUDIO.
---
A podcast by BlueDot Impact.
Learn more on the AI Safety Fundamentals website.
Kapitler
1. Deep Double Descent (00:00:00)
2. Model-wise double descent (00:02:28)
3. Sample-wise non-monotonicity (00:04:39)
4. Epoch-wise double descent (00:06:14)
85 episoder
Del
