Oh. Right. I didn't think about that interpretation .. Sorry if it seemed that way, I was just joking about the 80-20 rule in general, not about you.
Still interested to learn what triggered you :)
80% of the authors think they belong to the 20% ;)
(I do wonder what triggered your post..)
They probably had an MSX 😅
"In the interest of time I should agree with you. But that would just not be me." -every faculty meeting I've been to
Yes! No overreview or openleaf yet, though...
Any idea why this effect happens? 🤔
How high-res can you go? And where can I order framed versions for in my office? 😀
(Or should I keep it intentionally pixelated by NN-upsampling to my desired dpi 🤔)
Do you have hires variants? 🤩
Haha, might be good to brush up on it, as multiple of the "Nullius" podcast episodes are things he wrote about 🙂.
I do wonder why you think it's overly simplistic, but then I first will need to hear the podcast 🙂. Because I tend to agree with Strevens, but looking forward to being proven wrong 🙂
In "The Knowledge Machine", Strevens argues that there are no bad incentives in science, as long as empirical results come out 🙂.
(Excluding fraud..)
But I should first listen to this episode, before I speak my mind 😂. Nice topic 🙂
www.strevens.org/scientia/
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.
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 🙂.
