


Computer Science / Data Science professor at DePaul. Interactive Machine Learning for analytics - get the best of human and machine with artisan blending.


CISE CRII (~$175K 2-year projects for folks at non-R1s) will have a webinar for folks on Jul 20 from 2-330. Webinar signup at beta.nsf.gov/events/cise-res…; solicitation and FAQ at nsf.gov/pubs/2023/nsf23576/n… and nsf.gov/publications/pub_sum…. Pass it on...

Given the prompt, I expected it would complain, "what data?" Interesting that it interpreted marketing and sales as values of a categorical rather than as variables in their own right. I assumed it would give me an amusing lie, but I thought it would be a scatter plot.


Honestly, I can't believe that Spirit Halloween is allowed to get away with stuff like this:

Supporters Forum kicking off now. Come see what our fabulous supporters are up to! Panel to follow!
This tweet is unavailable

Occurs to me that one of the most productive (but rare?) ways to increase the standing of women and other marginalized groups in computing is to invite them to collaborate with you, especially if you're in the elite of your field 1/4

Whew, long journey but it's official: Associate Professor with Tenure !😊! It's been a real pain in the ass, but I learned, created and taught a lot, and that's pretty much the point :). Looking forward to the next chapter, once I figure out the title.

Way to go, @alvittao - kicking ass around the world! 😃🔥
Honored and humbled to receive the 2022 EuroVis Young Researcher Award 😊

But @TuckerCarlson if it's *red* light, then it's not #testicletanning, it's just 'testical toasting', maybe 'nut roasting'?

#Wordle bug :( ... It let me finish yesterday's game after midnight but now it's locked me out of today. streak broken :( I can make do with absurdle and obscurdle ⛅

theonion.com/cdc-announces-p… "Walensky added that if Americans took away one easy lesson from the pamphlet, she hoped it would be P(H|E) = (P(E|H) *P(H))/P(E).

Wow, I wonder how this would have looked if they knew what those mean? 🤣😟🤣 #data #DataScience Good to see #Datavisualization #datavis #ieeevis on top, though!
This is from an actual @HarvardBiz article (Oct 2018) that says learning statistics and mathematics are both 'time-consuming to acquire' and 'not useful' & should therefore be ignored. How can you do data science or dataviz well without those skills? | hbr.org/2018/10/prioritize-w…


Here is a very good reason why the Nyquist–Shannon sampling theorem requires that your function is low-pass before you sub-sample to downscale. If you just sub-sample without smoothing, a bad guy can place another image exactly on the pixels you sub-sample. Adversarial aliasing.
image-scaling attacks are wild small dots added to the image on the left turns it into the image on the right when downscaled could make auditing ML systems very tricky if you only look at the original images...

Asking a question on Twitter: Q: “Can someone recommend a good spoon?” A1: "I like the Flatware-2100” A2: “Why do you want a spoon when a straw works just as well” A3: “Just drink out of the bowl” A4: “Most restaurants let you use a spoon when you dine there."