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.

ML for Beginners GitHub

188 pointsby dunwaldoover 1 year ago

7 comments

TextBlobover 1 year ago
Is there a polite, constructive way to tell him no word has been put into the &quot;original author&#x27;s mouth&quot;?<p>What he&#x27;s reading there is just the following sentence in the book, separated with a comma...<p>&gt; TextBlob does a pretty good job at the translation: &quot;C&#x27;est une vérité universellement reconnue, qu&#x27;un homme célibataire en possession d&#x27;une bonne fortune doit avoir besoin d&#x27;une femme!&quot;.<p>It can be argued that TextBlob&#x27;s translation is far more exact, in fact, than the 1932 French translation of the book by V. Leconte and Ch. Pressoir:<p>&quot;C&#x27;est une vérité universelle qu&#x27;un célibataire pourvu d&#x27;une belle fortune doit avoir envie de se marier, et, si peu que l&#x27;on sache de son sentiment à cet egard, lorsqu&#x27;il arrive dans une nouvelle résidence, cette idée est si bien fixée dans l&#x27;esprit de ses voisins qu&#x27;ils le considèrent sur-le-champ comme la propriété légitime de l&#x27;une ou l&#x27;autre de leurs filles.&quot;<p>In this case, the translation informed by ML does a better job than the human translator who is unnecessarily putting words in the original author&#x27;s mouth for &#x27;clarity&#x27;.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;ML-For-Beginners&#x2F;blob&#x2F;main&#x2F;6-NLP&#x2F;3-Translation-Sentiment&#x2F;README.md#translation-and-sentiment-analysis-with-ml">https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;ML-For-Beginners&#x2F;blob&#x2F;main&#x2F;6-NL...</a>
评论 #38286337 未加载
ssgodderidgeover 1 year ago
Genuine question - is it more valuable to spend time ramping up on the ML basics, or to spend time building apps on top of the LLMs of the world?
评论 #38273611 未加载
评论 #38273198 未加载
评论 #38273525 未加载
评论 #38276520 未加载
评论 #38273317 未加载
评论 #38274680 未加载
评论 #38273384 未加载
评论 #38273423 未加载
评论 #38273976 未加载
评论 #38279967 未加载
评论 #38277567 未加载
评论 #38273543 未加载
评论 #38274639 未加载
dwaltripover 1 year ago
Relatedly, I recommend Andrej Karpathy’s “neural net: zero to hero” YouTube lectures. He breaks things down to the fundamentals in this really nice way, and you follow along in your own jupyter notebook.
throwaway19423over 1 year ago
Looks pretty nice (high-level skimming of content .. I work in the field but more DL focused. Mathy ML is my nemesis).<p>Two questions related to learning in general:<p>1) I feel I have a good undergrad level grasp of ML but not at a grad level grasp. The math is a bit overwhelming. I am not a fan of conferences like Neurips. Any one else try to conquer this challenge and have a story to share?<p>2) A bit off topic but the XR course they have linked on the page is also cute. It lists both Unity and MRTK. I have a Hololens2 and am curious about spatial mapping and awareness (just to learn at the moment). Any suggestions on what is a good stack for this area? I have very little 3D graphics background .. unity seems a bit too high for serious work and an engine seems too level :(
smithcoinover 1 year ago
Has anybody here completed this course?
whartungover 1 year ago
I’ll give it a look when I get off my phone. I’m trying to bootstrap some fundamentals for a personal project.<p>Currently working through some chapters of “AI. A modern approach “ book.
评论 #38273839 未加载
asylteltineover 1 year ago
Is this any good?
评论 #38274203 未加载