Anna Koop 😷🧑🌻 (@annakoop) header
Anna Koop 😷🧑🌻 (@annakoop) profile picture

Machine learning scientist, crafter, general enthusiast (she/her). Avid SJW representing only myself. I vent joy and anger and hope and pain and love on here.

Edmonton, AB
Joined October 2013
Photo by Anna Koop 😷🧑🌻 (@annakoop)Photo by Anna Koop 😷🧑🌻 (@annakoop)Photo by Anna Koop 😷🧑🌻 (@annakoop)Photo by Anna Koop 😷🧑🌻 (@annakoop)Photo by Anna Koop 😷🧑🌻 (@annakoop)Photo by Anna Koop 😷🧑🌻 (@annakoop)Photo by Anna Koop 😷🧑🌻 (@annakoop)Photo by Anna Koop 😷🧑🌻 (@annakoop)Photo by Anna Koop 😷🧑🌻 (@annakoop)
Anna Koop 😷🧑🌻 retweeted
If you work for Domino's, Pizza Hut, or Papa John's, I want to hear from you. I will not disclose your name or any information that could reveal your identity. Please fill out the form below. EVERYONE ELSE: Please RT to spread the word. forms.gle/vEpcsHkTaAch46cG7
8
260
3
206
Anna Koop 😷🧑🌻 retweeted
If you’re still wearing a mask when you go out, please retweet this tweet. I just want to see how much common sense is still out there.
1,777
172,624
2,868
100,586
β€œPer infection”!!
Replying to @1goodtern
The lungs – loss of consistency of elasticity equivalent to 15 years of aging per infection
4
Anna Koop 😷🧑🌻 retweeted
So, according to @CNNAfrica #Musk has closed the only office in Africa in Accra and provided no severance or next steps as he did in the states. Truly πŸ—‘οΈ but what else do we expect? #WokeAF
2
4
1
25
Okay this is amazing and now I want yards and yards of filmy fabric to play with. meowtalhead.tumblr.com/post/…
Hmm. This is a very good point. I need to modify how I express this. Consequences matter and β€œmental health” does not excuse real harm. And ABSOLUTELY does not imply harm. But harming others is different than β€œbehaving badly.”
β€œmental health doesn’t excuse bad behavior” is quite literally an ableist trope that i am tired of you people repeating just bc the internet told you to someone having a disability of the brain ABSOLUTELY excuses their behavior because BEHAVIOR BEGINS IN THE BRAIN, FOOL.
1
1
I really, really hate the conflation of β€œcaused actual avoidable harm to someone” with β€œviolated some social conventions” or β€œmade me feel awkward”
2
1
β€œGarbage in, model out” - no matter what data you use, you will create an ML model of some kind.
My AI Snake Oil book with @sayashk is now under contract with Princeton University Press! We’re starting a Substack to comment on AI hype in the news, separate the AI wheat from the chaff, and share our ideas as we draft the book. Read and subscribe here: aisnakeoil.substack.com/
2
Alex Kearney presenting "What should I know? Using Meta-Gradient Descent for Predictive Feature Discovery in a Single Stream of Experience." (I'm on this one!)
2
Final keynote! "Maintaining Plasticity in Deep Reinforcement Learning" @RichardSSutton @s_dohare
1
3
1
9
Q: "At some point you'll run out of capacity." I don't get why? You can reset the same node. A: "I don't see why you'd run out of capacity: at some point you might have to forget things. We're always going to have finite agents in this very big world."
1
Q: More utility measures possible. What about "doing the opposite"? "Spreading the utility across the weights instead of promoting such discrepancy". A: We have more results "ablation study for our utility measure"