luca
@fahrenheit
ML researcher, interested in math and probabilistic machine reasoning.
luca
The Fisher information matrix is simply the Hessian of KL divergence at the point where two distributions are equal.
Metacademy - Differential geometry for machine learning
your life is your life
don’t let it be clubbed into dank submission.
be on the watch.
there are ways out.
there is light somewhere.
it may not be much light but
it beats the darkness.
be on the watch.
the gods will offer you chances.
know them.
take them.
you can’t beat death but
you can beat death in life, sometimes.
and the more often you
... See moreOnly the future can tell. But we need to mend our ways. Otherwise, nihilism will win and we will deconstruct ourselves into oblivion. Maybe this is will be the million dollar question of the next century. What do we do, when we do not have to do anything?
refinement | llct
Linear algebra usually has two sides to explore: the algebraic interpretation and the geometric intuition. Usually the latter is much more useful to get a feel for things.
In the work with LLMs lies a deeper question, that I have not been able to answer for myself properly so far. I can use an LLM to extract information, summarise, distill, but it feels like I am fooling myself. The work that I have done is not done by me. I am have not made any connections in my brain. It feels like we should not use them for
... See more