Skip to content

Lilian Weng personal blog

Are deep neural networks dramatically overfitted? (2019)

lilianweng.github.io published 2019-03-14

<meta http-equiv=

Read on lilianweng.github.io → Discuss on HN (79) Archived copy

Points: 209
HN comments: 79
Submissions: 1
Cited by: 0 commenters

AI & Machine Learning Math & Algorithms 2021

On Hacker News

Submitted	Title on HN	Points	Comments
Apr 5, 2021	Are deep neural networks dramatically overfitted? (2019) by troyappel	209	79

More from Lilian Weng

All 14 posts →

Harness engineering for self-improvement

2026334 points80 comments Life, Learning & Writing details

LLM Powered Autonomous Agents

2023285 points176 commentscited by 3AI & Machine Learning details

The Transformer Family

2023254 points46 commentscited by 3AI & Machine Learning details

How to train large models on many GPUs? (2021)

2023216 points33 comments AI & Machine Learning details

Prompt Engineering: Steer a large pretrained language model to do what you want

2023190 points49 commentscited by 10AI & Machine Learning details

A (Long) Peek into Reinforcement Learning

2025160 points16 comments AI & Machine Learning details

Related posts from the same era

Building a Virtual Machine Inside ChatGPT

Jonas Degrave20222,029 points908 commentscited by 16 details

A first look at Unreal Engine 5

Unreal Engine Blog20201,734 points676 comments details

Whisper – open source speech recognition by OpenAI

OpenAI Blog20221,705 points481 commentscited by 5 details

AlphaFold: a solution to a 50-year-old grand challenge in biology

DeepMind Blog20201,473 points661 commentscited by 11 details

Stable Diffusion 2.0

Stability AI20221,368 points493 comments details

DALL·E: Creating Images from Text

OpenAI Blog20211,266 points267 commentscited by 25 details