Jaron Maene
@jjcmoon.bsky.social
PhD student @ KU Leuven | maene.dev | #neurosymbolic learning & #probabilistic reasoning
Something like this? arxiv.org/pdf/2410.06045
arxiv.org
October 4, 2025 at 9:06 AM
Something like this? arxiv.org/pdf/2410.06045
Reposted by Jaron Maene
The crazy thing about epicycles: at the time Kopernicus introduced his model they were far superior in terms of predictive power compared to the heliocentric model. This was still true when Kepler refined the model with ellipses. Epicycles had been extremely refined over time (capital+labor)
June 27, 2025 at 11:37 PM
The crazy thing about epicycles: at the time Kopernicus introduced his model they were far superior in terms of predictive power compared to the heliocentric model. This was still true when Kepler refined the model with ellipses. Epicycles had been extremely refined over time (capital+labor)
This was joint work with my amazing co-authors @pedrozudo.bsky.social and @vincentderk.bsky.social
April 23, 2025 at 8:14 AM
This was joint work with my amazing co-authors @pedrozudo.bsky.social and @vincentderk.bsky.social
And @gabventurato.bsky.social who presented on 3 different days!
March 5, 2025 at 4:18 AM
And @gabventurato.bsky.social who presented on 3 different days!
This was joint work with @lucderaedt.bsky.social.
The Gradient of Algebraic Model Counting
Algebraic model counting unifies many inference tasks on logic formulas by exploiting semirings. Rather than focusing on inference, we consider learning, especially in statistical-relational and neuro...
arxiv.org
February 27, 2025 at 11:47 PM
This was joint work with @lucderaedt.bsky.social.
We generalize backpropgation to semirings, which allows us to unify many learning tasks. This is similar to how inference on probabilistic models has been generalised (e.g. sum-product and max-product algorithms)
February 27, 2025 at 11:46 PM
We generalize backpropgation to semirings, which allows us to unify many learning tasks. This is similar to how inference on probabilistic models has been generalised (e.g. sum-product and max-product algorithms)
You can also do it without independence, but instead using distributivity, cf. arithmetic circuits.
November 29, 2024 at 8:16 PM
You can also do it without independence, but instead using distributivity, cf. arithmetic circuits.