Jan van Gemert

Bibliography cleanup is known to be harder than AGI. Same with successfully connecting a laptop with a projector. It's what we humans will be doing long after the robot takeover. 😇

I also like them. I think because they are tickling my brain to see meaning (where there's none)

Sometimes reminiscent of reviewing for cvpr 😉

I found The Knowledge Machine a solid read on what science is:

www.strevens.org/scientia/

Sorry for the unclarity 😅. I was wondering if a textbook is a "review" (it has limited novelty, I hope 😅). And, as such, if it's allowed on arXiv 🤔

I think I have seen them on arXiv in the past..

What about textbooks? 🤔

Well. At least they validate that deep learning methods might suffer from overfitting 😅

With some trepidation, I'm putting this out into the world:
gershmanlab.com/textbook.html
It's a textbook called Computational Foundations of Cognitive Neuroscience, which I wrote for my class.

My hope is that this will be a living document, continuously improved as I get feedback.

ABP investeert 825 miljoen in techbedrijf betrokken bij genocide in Gaza - The Rights Forum

But they are investing in this:

rightsforum.org/abp-investee...

Looks great!! Wonderful work. Is this tied to a research field? Or can it be used generally? 🤔

But more on topic: our university uses Microsoft everywhere. To change that would require a fight. One that I am not sure if I want to take upon me.. 😅

Our wonderful support staff person is about to retire, and I am afraid I will be relegated to "central IT" 😱

Paywall?

Haha, well, I was also thinking about CoordConv, the paper that added position info to convnets :)

(Which, interestingly, seems to go against that finding that convnets can already encode absolute position 🤔)

I've been also thinking about position embeddings :). I might investigate with a MSc student, although that is still a while before they start.. 😅

Ahaa! "negative impact" is a continuous term, not discrete.

Now I understand why they were even threatening to desk reject one of my papers that was already desk rejected ;)

(We didn't make it in time so it was already out..)

Oh, i found the "urgent! Risk of desk reject when co-author reviews not done" quite exciting ;)

Interesting! Even in a time where the last bastion of "knowledge based visual feature engineering" (ie: geometry) is replaced by learning (eg: VGGT) ?

Does it have to be 3 years? 🤔

For a failure, I can recommend my own TPAMI 2010 paper on "visual word ambiguity", exemplified by:
- not end-to-end (feature engineering)
- grayscale only
- convexity assumption
- small datasets
- ... (?)

I misread it as "chess cake" 😂.

Or should it be "check, cake"? (With the bishop 🙂).

You taught the 17y old to play well, nice position 🙂.

I'd like to propose the following norm for peer review of papers. If a paper shows clear signs of LLM-generated errors that were not detected by the author, the paper should be immediately rejected. My reasoning: 1/ #ResearchIntegrity

I'm catching up during the hiking holidays 🙂

Did we truly understand this ourselves? 😉

Gefeliciteerd! 🙂

@davidpicard.bsky.social is doing it in Paris, with cvpr pronounced in a French accent 🙂.

Incognito mode 🥸

Dutch nationalistic reading? 😉🇳🇱

Wonderful! I like nearly all of his work 🙂.

As i also do for most of the work of Neal Stephenson :)

Very interesting! I will have a look at those sources. Thank you.

I'm in machine learning (but not "AI" 😂) myself, and shortcut learning is one of the unsolved (practical?) problems in our field.

Definitely a language issue, my apologies.

I guess his point is: there's conflict between gains for science and gains for the scientist.

And that aligning them is an unsolved problem; in machine learning there's Bostrom's paperclip example 🙂. Also Goodhart's law.

Incentives are intended as rewards; but that having principals hurts personally.

Ie: to have principles and not "just go along with shady business" might hurt your career.

Eg: criticizing misconduct of famous/powerful people might get your next grant proposal rejected.