视频加载失败？在 YouTube 打开 ↗
我们必须给深度学习增加结构，因为……
WE MUST ADD STRUCTURE TO DEEP LEARNING BECAUSE...
AI 翻译，未经编辑审核
讲什么
Paul Lessard讨论用范畴论与单子增强神经网络可解释性、组合性，以及推理能力局限。
HN 网友推荐理由
HN 网友推荐理由：多在讨论Transformer递归能力和结构化深度学习时顺带引用。
摘要与推荐理由由 HackerTube 用 AI 生成，大榕 AI 翻译整理，未经编辑审核。
视频数据来源：HackerTube（https://hackertube.org），基于 Hacker News 社区推荐整理，依 ODC-By 1.0（https://opendatacommons.org/licenses/by/1-0/）许可使用。筛选与中文整理：大榕 darong.ai。
展开英文原文字段
Title
WE MUST ADD STRUCTURE TO DEEP LEARNING BECAUSE...
Summary
Machine Learning Street Talk interviews Paul Lessard about Categorical Deep Learning, which uses category theory and monads to make neural network architectures more interpretable and composable. They also discuss neural networks' limits in reasoning and unbounded computation.
Why HN
Mostly cited in passing, e.g. regarding claims that transformers cannot do recursion and as an example of structured deep learning work.
Primary topic
categorical deep learning