The Fisher information matrix is simply the Hessian of KL divergence at the point where two distributions are equal.

Differential geometry is all about constructing things which are independent of the representation

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

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 intell

... See more