Matrix Shuffle- Exchange Networks for Hard 2D Tasks

Ozoliņš, Emīls; Freivalds, Kārlis; Sosraks, Agris

doi:10.1109/ijcnn52387.2021.9533919

Search citation statements

Order By: Relevance

Paper Sections

Select...

Model1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2021

Publication Types

Select...

Other1

Relationship

Self Cite1

Independent0

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The loss is calculated from variable assignments out at each step, and the sum of all losses is minimized. Using the loss at each time-step has shown performance improvements [Palm et al, 2017, Amizadeh et al, 2019b, Ozolin , š et al, 2020 versus a single loss calculation at the end. Also, it enables using many more steps in evaluation than in training.…”

Section: Modelmentioning

confidence: 99%

Goal-Aware Neural SAT Solver

Ozolins,

Freivalds,

Draguns

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Modern neural networks obtain information about the problem and calculate the output solely from the input values. We argue that it is not always optimal, and the network's performance can be significantly improved by augmenting it with a query mechanism that allows the network to make several solution trials at run time and get feedback on the loss value on each trial. To demonstrate the capabilities of the query mechanism, we formulate an unsupervised (not dependant on labels) loss function for Boolean Satisfiability Problem (SAT) and theoretically show that it allows the network to extract rich information about the problem. We then propose a neural SAT solver with a query mechanism called QuerySAT and show that it outperforms the neural baseline on a wide range of SAT tasks and the classical baselines on SHA-1 preimage attack and 3-SAT task.Preprint. Under review.

show abstract

Section: Modelmentioning

confidence: 99%