Nicholas Wilkins

Sorry about all the spam, my twitter was hacked 🙃

[4 of 4] Good paper on this is arxiv.org/pdf/2108.02497…

[3 of 4] Please 1. report your standard errors from multiple runs and splits. 2. publish your hyperparmeters (and code and data), and how you got them (e.g. finetuning). Just because you can get it published / get your results to happen once does not mean that it's significant.

[1 of 4] Doing a lit review for some #ML. Unpopular opinion: Every time I do one of these I never cease to be amazed at the lack of rigorous reproducibility in the field and the amount of overclaims and "garbage science" (including from the big labs).

[2 of 2]If we had cut off the test early due to the technical difficulties, we would not have learned how tollerant users are to accuracy drops, latency spikes, etc (apparantly more tollerant than me)… It’s always a good day when you invalidate an assumption #UserExperience

[1 of 2]Interesting experience: due to tech difficulties (wifi, etc…) I thought that several usability tests had bombed, but when we got surprisingly good reviews from the users despite this, I remembered that we run experiments specifically to get these surprises #entrepreneurs

words cannot express my pain when a carefully crafted model that I poured my love and soul into is outperformed by the naive baseline T.T, which happens on a weekly basis #deeplearning #machinelearning

somehow just found out about numba lol, who needs vectorized operations anyway? (jkjk) #numba #python #numpy

@StevenBird Interesting framework to think about this especially with all the recent advances in #MachineLearning and Zero-resource Machine Translation (ai.googleblog.com/2022/05/24-new…)

When you talk about "low-resource" languages, do you mean: 1. would-be standardised languages; 2. local languages; or 3. contact languages? It matters, because the priorities for language technology are different in each case. More here: aclanthology.org/2022.acl-long.… #NLProc #LT4All

2AM thoughts: is engineering possible without crunchtime? #SoftwareDeveloper #programming #Engineering

@kareem_carr While 0.00005% does seem quite misleading, 100 accounts per day does seem quite small given how diverse twitter is (depending on what the objective is), especially if you're looking to establish a trend of the percentage of spam accounts.

I’m sorry but this argument from Elon’s lawyers is borderline statistically illiterate. It doesn’t matter at all that 100 accounts is a small percent of the total user base.

Just discovered the Bayes Rules book (bayesrulesbook.com). Wish I had this to lay the framework before delving into Probabilistic Graphical Models. Highly recommend to anyone looking to get into Bayesian learning. #MachineLearning #bayesian #learning

We are so excited for another day at @SummitAmericas hosted by @USChamber! They showcased business from all over the world, including Sign-Speak, a sign language recognition and avatar solution being created in the US! Let's see what the day holds #growwithgoogle #accessibility

Favorite part of having RSI is the random realization that it decided to flare up this week for no apparent reason 🙃. Any advice would be much appreciated. I kinda want to start coding by voice, but it's not gotten bad enough yet to justify the investment. #engineer #technology

@soheeyang_ The video was from a while ago so I'm sure setup is easier now, but I thought you might appreciate this vid from @tavisrudd youtube.com/watch?v=8Skdfd…. I've not had the chance to try it myself but I'll probably eventually need to adopt something like this as my RSI progresses.

It’s been 8 months since I've worked with burning pain on all fingers from typing. Three doctors say I may never be able to code again if I keep using a keyboard. I finally stopped my research pjt and it's a really tough time for one who loves to work. Any advice is appreciated..

The joy of choosing between rolling it yourself or using an large external dependency #tech #engineering #SoftwareEngineering

@mark_riedl Long ago, the ML practitioners lived together in harmony. Then everything changed when the PR department attacked…

Branding very large pre-trained neural language models as “foundation” models is a brilliant and disgusting PR stunt. It presupposes them as inevitable to any future in AI. I will violently eye-roll at anyone who uses that term in my presence.

@varcharr Or dual boot causing disk corruptions lol

@varcharr Tho although I find it an absolute necessity I do have to admit inadvertently breaking cuda than nuking all of my display drivers while trying to fix and needing to reset my system happens way more often than I’d like to admit :-(

Linux > Windows