Machine learning, statistics, software engineering. Occasionally, I do other things, too.
Durham, NC
Joined February 2014
- Tweets1.1K
- Following423
- Followers145
- Likes828
Listening to the most recent @strongerbysci fireside chat that talks about data analysis errors in Excel, and open up my computer this morning to find... 🤦
@GregNuckols
theverge.com/2020/8/6/213556…
Nick Haynes retweeted
What makes production ML hard?
- Cleaning, labeling, and augmenting data
- Troubleshooting training and ensuring reproducibility
- Deploying models and monitoring their real-world impact
To help, we're excited to announce our online production ML course:
course.fullstackdeeplearning…
Nick Haynes retweeted
Many people start attacking a problem by deploying the most sophisticated method possible with the belief that it will lead to the best results. I believe it might be better to chisel away at the complexity and find the simplest possible combination that expresses the key ideas.
Important to remember that BLEU (or ROGUE, or other quantitative metrics) don't tell the whole story - two texts w/ same metrics can have very different perceived levels of quality to human readers. xitter.cf/stanfordnlp/status/973…
We’d still put this in the hyping AI bucket and don’t really believe the translations are as good as a careful human’s. Nevertheless, this paper does examine and discuss measuring human parity much more carefully than most #dlearn papers that claim super-human performance…. xitter.cf/seb_ruder/status/97392…
Nick Haynes retweeted
Teams + Fans + Tech panel moderated by @YahooSports Michael Beshar looks at how new tech enables teams to build fan affinity & drive broader consumption of content @jaynebwise @nakanofrank #SMT18
Nick Haynes retweeted
Maybe progress in Vision/NLP/etc is not due to neural nets, but rather due to the influx of smart researchers, lots of compute, and industry pushes.
Focusing on a different paradigm (graphical models, evolution, ..) could’ve made the same amount, but different type, of progress.
The fundamental irony of Twitter: the short format allows your audience to exist, but bc the audience exists, you want a longer format.
"as a general principle of learning, it 'somehow smells right.'" Well, I'm convinced.
quantamagazine.org/new-theor…
Nick Haynes retweeted
The belief that stacking layers deeper leads to better models is just a myth pushed by the big DL lobby to sell more tensors
"It's not unusual to see team members literally inches away from a complete nervous breakdown." xitter.cf/jackclarkSF/status/908…
New jobs announced for @AndrewYNg startup. Description makes jobs seem anti people with families. Horrible message. xitter.cf/AndrewYNg/status/90805…
Better question: how many current users would stop using IG/WhatsApp if all FB users migrated to those platforms. xitter.cf/fchollet/status/900834…
