Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Scallop: A Neurosymbolic Programming Language

scallop-lang.github.io

Post reply on HN
Print view View original

11–20 of 30 posts

Re: Scallop: A Neurosymbolic Programming Language

#11

Post by hgir8937q63hlay »

rsfern wrote: post #2

The sum-of-NIST-digits CNN+logic example was really interesting: https://scallop-lang.github.io/tutorial.html#section-10 Anybody familiar with the space have pointers to good introductory material on this field? Or terms to search on to get at current work - differentiable logic?

The recent survey on Neurosymbolic Programming is a great introduction to the field: https://twitter.com/swarat/status/1474105098401943555 (pardon the Twitter link). I don't think the full version is publicly available, but I suspect you might be able to get access to it if you DM someone involved.

Other than that, here are some names of people working in this field that you might be able to find representative work from:

- Mayur Naik, UPenn (whose group I think were behind Scallop?) - Swarat Chaudhuri (and maybe also Isil Dillig), UT Austin - Luc de Raedt, KU Leuven (whose earlier work on Statistical Relational AI is very similar to the Scallop style of neurosymbolic work - I think there's a good textbook available on this) - Guy van den Broeck, UCLA - Armando Solar-Lezama, MIT

If you're more interested in the logic side of things then maybe some of MIRI's (https://intelligence.org/) older work may be of interest.

There's also a lot of people who are interested in neuro-symbolic stuff in the wider sense. You can find out more here: http://www.neurosymbolic.org/index.html. If you sign up for the mailing list, there are monthly (or bi-monthly? I can't remember) talks that are open to the public. You can even find recordings of past talks on Armando Solar-Lezama's youtube channel.

Hope this helps!

Re: Scallop: A Neurosymbolic Programming Language

#13

Post by nudpiedo »

doctor_eval wrote: post #9
nudpiedo wrote: post #3

it looks really good, the sort of trully new generation of programming languages we need, bringing new constructs and solutions for the new world challenges and solutions as the previous abstractions are already falling short. I wish it would be clear on which platforms does it run, because for its description I can only read about python's integration, which is great, but not sure whether I could run a "client" on j…

Download page has platforms: https://scallop-lang.github.io/download.html Seems to be MacOS (M1 and x86) and Linux x86.

that's true although that's not a target platform for which it compiles to. Later today I've seen the runtime appears to be written in rust, so it might be possible to port it to many architectures althought at the moment it looks to be a desktop only runtime/embedded library.

Re: Scallop: A Neurosymbolic Programming Language

#14

Post by troelsSteegin »

ducktective wrote: post #7

Can some one share some links explaining this field? https://www.youtube.com/watch?v=HhymId8dr5Q This seems to be literally the future. What am I missing?

The video links to an overview of the backing research program, https://medium.com/swlh/neurosymbolic-ai-to-give-us-machines... , and from there I would look at the MIT site: https://mitibmwatsonailab.mit.edu/category/neuro-symbolic-ai...

The underlying big idea, as quoted from the medium article:

They posit that humans are born with a pre-programmed rough understanding of the world, in some ways analogous to the game engines used to build interactive immersive video games. This “game engine in the head” provides the ability to simulate the world and our interactions with it, and serves as the target of perception and the world model that guides our planning.

Crucially, this game engine learns from data, starting in infancy, to be able to model the actual situations — the endless range of “games” — we find ourselves in. It is approximate yet gets more and more efficient — to the point that very quickly, humans make instant mental approximations that are good enough to thrive in the world. And, the researchers think, it’s possible to replicate this type of system in a machine by embedding ideas and tools from game engine design inside frameworks for neurosymbolic AI and probabilistic modeling and inference known as probabilistic programs.

Re: Scallop: A Neurosymbolic Programming Language

#16

Post by abrax3141 »

The idea that you had to instrumentally combine perceptual and symbolic reasoning has been around since at least the 1970s and has been implemented variously (see, for example: Hermina J.M. Tabachneck-Schijf, Anthony M. Leonardo, Herbert A. Simon (1997) CaMeRa: A Computational Model of Multiple Representations). What those models didn't do is learn, but just pouring learning into that sort of model and hoping it will magically become a GAI seems like an implementation idea without a theory.

Re: Scallop: A Neurosymbolic Programming Language

#18

Post by rsfern »

hgir8937q63hlay wrote: post #11
rsfern wrote: post #2

The sum-of-NIST-digits CNN+logic example was really interesting: https://scallop-lang.github.io/tutorial.html#section-10 Anybody familiar with the space have pointers to good introductory material on this field? Or terms to search on to get at current work - differentiable logic?

The recent survey on Neurosymbolic Programming is a great introduction to the field: https://twitter.com/swarat/status/1474105098401943555 (pardon the Twitter link). I don't think the full version is publicly available, but I suspect you might be able to get access to it if you DM someone involved. Other than that, here are some names of people working in this field that you might be able to find representative work…

Awesome, thanks!

I think I found a full preprint on the authors site (pdf) https://www.cs.utexas.edu/~swarat/pubs/PGL-049-Plain.pdf

Re: Scallop: A Neurosymbolic Programming Language

#19

Post by rsfern »

mark_l_watson wrote: post #12

Someone posted another link to Scallop on HN a few days ago. I am looking forward to the next version that will have interop with Python and PyTorch.

I saw it on Sunday, I think this is second chance pool in action

There’s a PyTorch example here: https://scallop-lang.github.io/tutorial.html#section-10

Re: Scallop: A Neurosymbolic Programming Language

#20

Post by rsfern »

sebastianconcpt wrote: post #15

What's the applicability? What are some concrete examples of problems that you would solve with it? Why is a better fit than using you preferred language with your own code?

Their NeurIps paper is all about scalable training/inference in ML systems that combine deep learning for perception and symbolic logic for e.g. visual question answering

pdf: https://www.cis.upenn.edu/~mhnaik/papers/neurips21.pdf

Post reply on HN