111–120 of 174 posts
All the stuff coming out of the Koka and Effekt development. In particular last week i read their FBiP2 paper https://www.microsoft.com/en-us/research/uploads/prod/2023/0...
All the stuff coming out of the Koka and Effekt development. In particular last week i read their FBiP2 paper https://www.microsoft.com/en-us/research/uploads/prod/2023/0...
When I google for "koka effekt" I get pages in German about the effects of cocain. They should maybe reconsider the "Koka" part of the project name?
Earlier quoted context omitted.
When I google for "koka effekt" I get pages in German about the effects of cocain. They should maybe reconsider the "Koka" part of the project name?
These are two different languages, see https://effekt-lang.org/ and https://koka-lang.github.io/koka/doc/index.html -- although I believe that the FP^2 work mentioned by OP currently only works in Koka (and perhaps soon in Lean; https://leanprover.github.io/ )
That said i am slowly writing my own language that will probably use ideas from both :D
I think you meant "recently published paper" but others are bringing up old stuff. I've always enjoyed Einstein's (translated) papers. They are both precise and readable, and his reputation for genius is well deserved! This one is interesting, "On the Influence of Gravitation on the Propagation of Light" you can read here: https://einsteinpapers.press.princeton.edu/vol3-trans/393 . This was his initial stab at GR. It…
All the stuff coming out of the Koka and Effekt development. In particular last week i read their FBiP2 paper https://www.microsoft.com/en-us/research/uploads/prod/2023/0...
Thanks, I am surprised and delighted to see our paper here! We also wrote a follow-up recently, which you may enjoy: https://www.microsoft.com/en-us/research/uploads/prod/2023/0...
I am slooooowwly working on my own language that is planned to use work from both you and the Effekt team, so i may send you all an email in the future when i start having questions.
Integral Neural Networks (CVPR 2023 Award Candidate), a nifty way of building resizable networks. My understanding of this work: A forward pass for a (fully-connected) layer of a neural network is just a dot product of the layer input with the layer weights, followed by some activation function. Both the input and the weights are vectors of the same, fixed size. Let's imagine that the discrete values that form these…
Nice. I was wondering if something like this is possible a few days ago. The next step would be somehow extending the discrete->continuous concept to layers.
Earlier quoted context omitted.
I think we're conflating two things: shallow/classic ML is not symbolic AI. I'm not sure "ML" even encompasses anything "symbolic"; I see symbolic AI and ML as subfields with little overlap. I'm not saying symbolic AI has been GPU accelerated in the past, but that non-deep ML has been.
There is no agreement on the exact meaning of ML and AI. They are often used interchangeably. And for good reason, because it's all about getting computers to learn. We should not squabble about semantics. Can you point towards papers that report substantial GPU acceleration on what you call "non-deep ML"?
Earlier quoted context omitted.
Happens far more than you think. It can be an innocent (sort of) mistake, where authors see the citation in a previous paper and simply copy it into their own.
This feels like something that would, at large scale, be unhealthy for science as a whole. While existing papers have already gone through their own quality checks, this enables bad, misleading, or false statements to propagate which can end up being a blow to the credibility of the entire model. Shouldn't there be an ethical duty to due one's due diligence?
Earlier quoted context omitted.
Thanks, I am surprised and delighted to see our paper here! We also wrote a follow-up recently, which you may enjoy: https://www.microsoft.com/en-us/research/uploads/prod/2023/0...
Oh nice thanks! I am slooooowwly working on my own language that is planned to use work from both you and the Effekt team, so i may send you all an email in the future when i start having questions.
"Overview of SHARD: A System for Highly Available Replicated Data" it's the first paper to introduce the concept of database sharding. It was published in 1988 by the Computer Corporation of America. It is referenced hundreds of times in many classic papers. But, here's the thing. It doesn't exist . Everyone cites Sarin, DeWitt & Rosenb[e|u]rg's paper but none have ever seen it. I've emailed dozens of academics, libr…
Going through the bibliography of other people's papers and theses, looking for papers that you better cite "for good luck", or because "you gotta cite that one" is a classic PhD student behavior (I've done it) and it's not terribly surprising that something like this can happen. In fact I'd expect it to be much more widespread...
Of course if nobody can get their hands on a particular work, as seems to be the case here, that makes things kind of hard. But I'd expect most works you need to cite in a fast-moving field such as CS to be available at least somewhere, even if it takes a bit of effort.