EP37 | 深談Deepseek (下)：R1推理模型、強化學習、模型蒸餾、UC Berkeley PhD用小模型復現R1

from 數創實驗室 - AI時代的學習指南 · host Vincent在數創

#### 本期簡介 Deepseek-R1 以「純自動化 GPRO」取代 RLHF 的人力標註，成功降低訓練成本並造就令人驚嘆的「aha moment」。相較 OpenAI 的 o1，Deepseek-R1 更具規模化優勢。本集剖析其強化學習邏輯、封禁爭議及模型蒸餾風波、以及對於應用端的啟示。 #### 關於主持人 Vincent Chen (www.linkedin.com/in/hsiang-hao-chen-53443593) 數創智能CEO / 數創實驗室創始人, Podcast播客主理人美國財星500強電商大廠 | 數據團隊主管台灣零售行業上市公司 | 資料技術處處長 AI & 大數據跨國經驗10年+ | 跨國反欺詐 | 智能行銷 & 推薦系統英國全球百大 Data Science & 台灣交大MBA雙碩士 #### 意見回饋歡迎回饋您希望收聽的AI主題 : https://bit.ly/40Q8PT6 #### 相關連結 LINE社群入群連結 : https://bit.ly/3TU9K0I 數創實驗室官網 : https://datainnolab.ai 聯繫數創實驗室 : [email protected]

Episode metadata supplied by the publisher feed · Published Feb 16, 2025

Embed this episode

Attribution link and audio player

Ready to play

EP37 | 深談Deepseek (下)：R1推理模型、強化學習、模型蒸餾、UC Berkeley PhD用小模型復現R1

0:00 25:37

1×

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Share this episode

Similar Episodes

No similar episodes found.

Similar Podcasts

CISO Perspectives (public) N2K Networks This season on CISO Perspectives, host Kim Jones explores some of the challenges of leading through uncertainty. We explore the complexity of the changing nature of regulation and working with the federal government, the evolution of privacy and fraud, and how emerging technologies like AI and quantum computing are changing cyber. When you don’t know what questions to ask, you’re afraid to ask, or don’t know who to ask, CISO Perspectives provides the foundation for learning in this brave new world.

Frequently Asked Questions

How long is this episode of 數創實驗室 - AI時代的學習指南?

This episode is 25 minutes long.

When was this 數創實驗室 - AI時代的學習指南 episode published?

This episode was published on February 16, 2025.

Can I download this 數創實驗室 - AI時代的學習指南 episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.

URL copied to clipboard!