4 - Help! There is no ground truth

Naked Data Science

Naked Data Science에서 제공하는 콘텐츠입니다. 에피소드, 그래픽, 팟캐스트 설명을 포함한 모든 팟캐스트 콘텐츠는 Naked Data Science 또는 해당 팟캐스트 플랫폼 파트너가 직접 업로드하고 제공합니다. 누군가가 귀하의 허락 없이 귀하의 저작물을 사용하고 있다고 생각되는 경우 여기에 설명된 절차를 따르실 수 있습니다 https://ko.player.fm/legal.

5+ y ago 17:53

MP3•에피소드 홈

저장한 시리즈 ("피드 비활성화" status)

When? This feed was archived on February 27, 2024 11:13 (1+ y ago). Last successful fetch was on November 09, 2024 16:14 (10M ago)

Why? 피드 비활성화 status. 잠시 서버에 문제가 발생해 팟캐스트를 불러오지 못합니다.

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.

Why you can't only rely on existing methods to evaluate your work, what to do when you don't have evaluation data, what to do when there is no ground truth, why some mistakes are much more important than others, and the importance of ongoing evaluations.
BTW, if you are not a data scientist yet, but want to become one, you should really attend our webinar. We will demystify the transition into data science. We will show you the most effective way to build your skills. And we will advise you on the four possible options you can take to go from where you are to landing a data science job in as little as 9 months. Find out more here.

챕터

1. 4 - Help! There is no ground truth (00:00:00)

2. How do you know when you have solved a problem (00:01:17)

3. Why you shouldn't only rely on existing e valuation methods (00:01:55)

4. Under-estimating the importance and effort of evaluation (00:02:42)

5. The gap between offline evaluation metrics and business impact (00:04:02)

6. Not all mistakes are equal (00:04:37)

7. Help! I don't have evaluation data (00:05:09)

8. Please ask for money (00:06:28)

9. Why don't you just evaluate online (00:07:59)

10. Help! There is no ground truth (00:09:48)

11. Forget about existing metrics. Find the most embarrassing data (00:12:38)

12. One-shot vs. ongoing evaluation (00:13:52)

13. The system you build doesn't exist in isolation (00:14:38)

14. The one practical thing (00:16:18)

35 에피소드

#Tech #Naked Data Science #Data Science #Data Scientist #Data-driven Innovation #Cross-functional Team #Data Engineering #Machine Learning #Artificial Intelligence

4 - Help! There is no ground truth

Naked Data Science

35 subscribers

published 5+ y ago

MP3•에피소드 홈