Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @dan_s_becker
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @dan_s_becker
-
Rank ordering of outcomes for my grad school classmates: Those who got tenure track jobs and missed tenure are least satisfied today Next worst? People who have only had adjunct faculty jobs People who got tenure are happy Those who just skipped academia are happiest of allhttps://twitter.com/JohnHolbein1/status/1223621187923824645 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Though I'm perplexed how a model minimizing perplexity came up with "Hayvard" "You were trying to steer it elsewhere." That's superhuman level conversation.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This is amazing
@jamie_hall . When you told me about this project, I had no idea it was *this* good. Nice work Even the randomly selected samples in the appendix are impressive.https://twitter.com/kcimc/status/1222378902821068800 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Dan Becker proslijedio/la je Tweet
Applying machine learning to the real world is commonly an optimization problem on top of the ML predictions. My former colleague
@dan_s_becker built and awesome demo of this at http://why.decision.ai/ with "The Mango Challenge", and this is the core thesis for his new companyHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
What would a more applied approach to AI look like? I think I have the answer. So I'm leaving Google and Kaggle to build a business around it. Check it out at http://why.decision.ai Want help getting more than predictions, so you can optimize decisions? Let's talk. I can help
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Dan Becker proslijedio/la je Tweet
I wasn't aware of SHAP before, but I'm a really big fan, now. The Shap library produces beautiful visualizations as well, and is actively maintained!https://github.com/slundberg/shap
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Dan Becker proslijedio/la je Tweet
Highly recommend
@dan_s_becker 's Machine Learning Explainability course. One of the many gems in this course is the tutorial on SHAP and the accompanying code. Its a brief set of tutorials in notebooks, but very worthwhile:https://www.kaggle.com/learn/machine-learning-explainability …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I thought I ought to prefer a "grammar of graphics" library. But... ¯\_(ツ)_/¯
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I've historically been luke-warm about matplotlib But a multi-year tour of other python graphing libraries has me more appreciative Is flexible enough for anything I'd want... and while others might have clever API's, the comprehensive matplotlib docs make up for it.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Dan Becker proslijedio/la je Tweet
@kaggle is hiring a data science educator!https://www.kaggle.com/general/124968Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Their demo at https://www.youtube.com/watch?v=B2iAodr0fOo … doesn't appear to be just some curated happy path. It's pretty similar to my first impressions using the product.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I heard about
@streamlit earlier this week Tried it for the first time this morning
Holy smokes
I'm not sure I'll ever write a Jupyter notebook again. They might still have some use case?
But Streamlit is shockingly nice to use
Thx @HamelHusain for telling me about itPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Financial returns to college are shrinking: https://www.stlouisfed.org/~/media/files/pdfs/hfs/is-college-worth-it/emmons_kent_ricketts_college_still_worth_it.pdf … Enrollment numbers have decreased ~1% a year since 2010 People still tell me college education will always be necessary for a good career, but I think they've missed trends that are already happening
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Look at what's happened. Predict it will keep happening.https://twitter.com/SusannaLHarris/status/1207769269523505152 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Dan Becker proslijedio/la je Tweet
Blown away by the intuitive n simple understanding of overfitting n underfitting in DecisionTree. Obsessed with
@kaggle micro-courses.@dan_s_becker sir, a humble request to add more ML algos, may be in a separate micro-course would be a huge benefit to all learners. Ty ty ty!!!Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Dan Becker proslijedio/la je Tweet
At some point, you have to decide how to raise the children.https://twitter.com/ProfArbel/status/1195920031600672769 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
An experiment: what is the most interesting way to take this further? Color coded map? Spending per capital? Percent of GDP? Map with visual sizes shown proportional to military spend? The meta question: do we get to something cool if we iterate on ideas in Twitter threadhttps://twitter.com/antgoldbloom/status/1193764018281861121 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Dan Becker proslijedio/la je Tweet
“How should we rank which colleges are the best?” “Let’s start with a list of those that reject the most people.”https://twitter.com/garrytan/status/1191963073487233025 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Github's new "State of The Octoverse" report is fascinating. https://octoverse.github.com/ One interesting fact (among many in the report): 5X growth in number of open source developers since 2014.pic.twitter.com/65F8YgUAh7
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kaggle is hiring an AI educator. Want to have a global impact? Here's your chance to share your skills with 10000s of data scientists a month.https://www.kaggle.com/general/116083
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.