Is the source code available? When I go to the the GH I see that the project is archived. Am I missing something here?
Scallop: A Neurosymbolic Programming Language
21–30 of 30 posts
Re: Scallop: A Neurosymbolic Programming Language
#22How does this compare to NeuraLogic?
Re: Scallop: A Neurosymbolic Programming Language
#23The "CLEVR" example reminds of Terry Winograd's SHRDLU program https://hci.stanford.edu/winograd/shrdlu/ which was written in 1968-1970.
Re: Scallop: A Neurosymbolic Programming Language
#24How does this compare to NeuraLogic? https://github.com/LukasZahradnik/PyNeuraLogic
I have been a few months into PyNeuraLogic because of its focus on Relational Deep Learning (in particular Lifted Relational Neural Networks). I would say the main selling point is extending GNNs (Graph Neural Networks)
From what I can see on the Scallop website, the focus is on vision and NLP.
So both are similar approaches combining deep learning with symbolic reasoning (and both are based in Datalog) but the problems they are tackling are quite different. Also, both approaches have made it to top conferences like NeurIPS and ICLR, so I guess this field is gaining momentum.
Re: Scallop: A Neurosymbolic Programming Language
#25How does this compare to NeuraLogic? https://github.com/LukasZahradnik/PyNeuraLogic
I have been a few months into PyNeuraLogic because of its focus on Relational Deep Learning (in particular Lifted Relational Neural Networks). I would say the main selling point is extending GNNs (Graph Neural Networks) From what I can see on the Scallop website, the focus is on vision and NLP. So both are similar approaches combining deep learning with symbolic reasoning (and both are based in Datalog) but the probl…
Just based on the docs, on the lowest level they both create a mapping from input features to relations. Then NeuraLogic has an example for implementing GCN like message passing with a simple relational rule:
``` node2(X) Do you know, is it possible to implement something on Scallop as well, or are the differences much larger?
Re: Scallop: A Neurosymbolic Programming Language
#26At a glance, this looks like a new syntax in the Prolog family (with some other special stuff). Erlang, which kept Prolog syntax but lost its semantics, has a similar new syntax in Elixir.
Datalog. > in the Prolog family > Scallop is a full-fledged logic programming language based on Datalog [...] a logic rule-based query language for relational databases. [...] Scallop is a scalable Datalog solver equipped with support for discrete, probabilistic, and differentiable modes of reasoning
Yes, but Datalog has traditionally kept the Prolog syntax as a subset of Prolog. This is a new syntax.
Re: Scallop: A Neurosymbolic Programming Language
#27it 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…
The new generation of programming languages will just be plain old English text
Re: Scallop: A Neurosymbolic Programming Language
#28Looks quite interesting. Anyone here who has used it in practice?
It only just dropped, so no one has used it in anger yet. I've written a couple of small things in it today though.
It just seems like such a lovely little language, but prologs are. It is pretty damn great to be able to attach probabilities to things and prolog away.
Re: Scallop: A Neurosymbolic Programming Language
#29Earlier quoted context omitted.
I have been a few months into PyNeuraLogic because of its focus on Relational Deep Learning (in particular Lifted Relational Neural Networks). I would say the main selling point is extending GNNs (Graph Neural Networks) From what I can see on the Scallop website, the focus is on vision and NLP. So both are similar approaches combining deep learning with symbolic reasoning (and both are based in Datalog) but the probl…
Just based on the docs, on the lowest level they both create a mapping from input features to relations. Then NeuraLogic has an example for implementing GCN like message passing with a simple relational rule: ``` node2(X) Do you know, is it possible to implement something on Scallop as well, or are the differences much larger?
The GCN implementation is based on the concept of templating (or lifting) which is not exploited in Scallop. In fact, this is the key idea of Neuralogic for joining deep learning and relational-logic representations.
It is explained in the paper "Beyond Graph Neural Networks with Lifted Relational Neural Networks" (https://arxiv.org/abs/2007.06286) and you also have a series of blog posts at https://medium.com/@sir.gustav
Re: Scallop: A Neurosymbolic Programming Language
#30The 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…
Did I miss where the developers are claiming this toolset will help implement GAI?