TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

“When you have enough data, sometimes, you don’t have to be too clever”

45 pointsby smarterchildover 13 years ago

5 comments

keithpeterover 13 years ago
When data is easy to collect, someone will ask you to collect it and someone else will query the data and compile a report with <i>percentages</i> in it. Then someone else will worry about some of the <i>percentages</i> being less or more than some <i>benchmark</i>. Then your work life will become less happy.<p>Example 1: Some years ago, I had to sit through a meeting where a committee worried about a <i>2% drop</i> in satisfaction scores on a student questionnaire. No-one checked how many replies were involved (around 400, so it worked out to about 6 people less in the second year than the first as the ratings were something like 75%).<p>Example 2: I recently had to add comments in a record system about students whose attendance <i>percentage</i> had dropped below 90%. That was 8 weeks into the course...
tambourine_manover 13 years ago
Sometimes I get the feeling that when we had less data, we were forced to think harder and more daringly. I feel we lack new groundbreaking theoretical framework because of this.<p>I don't know if Newton's law's would jump out of the paper if you simply threw a ball at one million different vectors.
评论 #3365430 未加载
评论 #3365269 未加载
评论 #3365528 未加载
评论 #3365274 未加载
评论 #3365277 未加载
DanielRibeiroover 13 years ago
This is pretty much the same conclusion Ilya Grigorik (founder of postrank, which was recently bought by Google) came to: <a href="http://vimeo.com/22513786" rel="nofollow">http://vimeo.com/22513786</a>
glimcatover 13 years ago
Naive Bayes: the "good enough" classifier.
joe_the_userover 13 years ago
Looking at the video, you could interpret his statement two ways. Either, the headline - <i>“When you have enough data, sometimes, you don’t have to be too clever”</i> OR the sort-of-opposite - <i>"AI has made so little progress that we don't anything much better than naive Bayes"</i>
评论 #3365457 未加载
评论 #3365944 未加载
评论 #3365461 未加载