Amulya_lossfunction

Like Cornelius Agrippa I am god, I am hero, I am philosopher, I am demon and I am world,which is a tedious way of saying I do not exist

[Amulya_lossfunction @amulya_23]

Just wrapped up XplainMD — A Multi-Relation Biomedical Link Prediction & Explanation tool

GitHub: https://t.co/tfpsP0KDWB
Blog: https://t.co/91hGvUgsht

#GraphNeuralNetworks #ExplainableAI #Bioinformatics #LLM #MachineLearning #PrecisionMedicine

[a @yyioom]

all roads lead back to me isolating myself

[Amulya_lossfunction @amulya_23]

@pretty_sarlin Ants

[Amulya_lossfunction @amulya_23]

@elonmusk I thought it's just elon with a wig as the news reporter

[François Chollet @fchollet]

There's a broadly held misconception in AI that methods that scale well are simple methods -- even, that simple methods usually scale. This is completely wrong.

Pretty much none of the truly simple methods in ML scale well. SVM, kNN, random forests are some of the simplest methods out there, and they don't scale at all. Meanwhile "train a transformer via backprop and gradient descent" is a very high-entropy method, easily 10x more complex than random forest fitting. But it scales very well.

Further, given a simple method that doesn't scale, it is usually the case that you alter it to make it scale by adding a lot of complication. For instance, take a simple a simple combinatorial search-based method (not scalable at all) -- you can make it scale by adding deep learning guidance (which blows up complexity). Scalability usually belongs to high-entropy, complex systems.

[✒️ @Literariium]

— Unknown

[Elon Musk @elonmusk]

😑

[Rajat @rajatsandeepsen]

Dr. @ylecun traveled all the way to India just to say "fuck the LLMs" 😭

[Sama Hoole @SamaHoole]

>Be Bryan Johnson
>Decide at 42 that death is optional if you have enough money and no personality
>Hire a team of 30 doctors to monitor your every function
>Eat 1,977 calories of carefully engineered beige paste per day
>Take 111 supplements
>Go to bed at 8:30pm
>Inject yourself with your own son's plasma like some kind of polite vampire
>Spend $2 million per year on this
>Biological age reduced by approximately 5 years after 3 years of effort
>Announce you are "reversing aging"
>Look somehow older than when you started
>Go on podcasts to explain that you no longer experience joy, but your telomeres are excellent
>Announces optimal body temperature is now 35°C
>Says it’s “metabolically efficient”
>Essentially refrigerated

[PenPencilDraw @penpencildraw]

AI impact.

[Reads with Ravi @readswithravi]

Discipline:

[Pedro Domingos @pmddomingos]

It's mind-blowing that the entire AI revolution is being driven by a single 10-line algorithm.