luca
@fahrenheit
ML researcher, interested in math and probabilistic machine reasoning.
luca
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 moreDread accompanies me through life but it is not without consolation | Aeon Essays
aeon.coThe Fisher information matrix is simply the Hessian of KL divergence at the point where two distributions are equal.
Metacademy - Differential geometry for machine learning
Differential geometry is all about constructing things which are independent of the representation
Metacademy - Differential geometry for machine learning
"Don’t think. Thinking is the enemy of creativity. It’s self-conscious, and anything self-conscious is lousy. You can’t try to do things. You simply must do things."
- Ray Bradbury
The glow in the centre of the k-space image represents the lower spatial frequencies, which contains the bulk of the image contrast information. As we move away from this central glow, the finer details and edges, representing the higher spatial frequencies
Nadav Levi • Visualising MRI data in Python
The risk in designing any personal knowledge system lies in the overemphasise of the acquisition system to the detriment of the review system. Acquisition can masquerade as work, but collecting without review is pseudo-work.
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