思想与社会2020 · 分享于 Hacker News
Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
探索《Every Model Learned by Gradient Descent Is Approximately a Kernel Machine》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Yscottlocklin ·
Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
406 赞同107 评论
Yaflip ·
Ask HN: What things are happening in ML that we can't hear over the din of LLMs?
364 赞同99 评论
Yumangkeshri ·
Does GPT-2 Know Your Phone Number?
321 赞同155 评论
Yagnosticmantis ·
Deep learning is hitting a wall?
274 赞同250 评论
Yhomarp ·
Pathways Language Model (PaLM): Scaling to 540B parameters
235 赞同207 评论
YAnon84 ·
Every model learned by gradient descent is approximately a kernel machine (2020)
176 赞同136 评论
Ythe__prestige ·
A new link to an old model could crack the mystery of deep learning
173 赞同66 评论
Ytibbar ·
Using GPT-3 to pathfind in random graphs
165 赞同79 评论
Y1wheel ·
Do Machine Learning Models Memorize or Generalize?
7 赞同0 评论
Ybreck ·
Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
4 赞同0 评论
YLordNibbler ·
Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
4 赞同0 评论
Ydeathflute ·
Deep learning networks are approximately kernel machines
2 赞同1 评论
Yoptimalsolver ·
Every Model Learned By Gradient Descent Is Approximately A Kernel Machine (2020)
2 赞同0 评论
Ygardenfelder ·
Google researchers deal a major blow to the theory AI about to outsmart humans
2 赞同1 评论
Ycgadski ·
When Gradient Descent Is a Kernel Method
1 赞同0 评论