English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

SATNet is an award-winning MAXSAT solver that can be used to infer logicalrules and integrated as a differentiable layer in a deep neural network. It hadbeen shown to solve Sudoku puzzles visually from examples of puzzle digitimages, and was heralded as an impressive achievement towards the longstandingAI goal of combining pattern recognition with logical reasoning. In this paper,we clarify SATNet's capabilities by showing that in the absence of intermediatelabels that identify individual Sudoku digit images with their logicalrepresentations, SATNet completely fails at visual Sudoku (0% test accuracy).More generally, the failure can be pinpointed to its inability to learn toassign symbols to perceptual phenomena, also known as the symbol groundingproblem, which has long been thought to be a prerequisite for intelligentagents to perform real-world logical reasoning. We propose an MNIST based testas an easy instance of the symbol grounding problem that can serve as a sanitycheck for differentiable symbolic solvers in general. Naive applications ofSATNet on this test lead to performance worse than that of models withoutlogical reasoning capabilities. We report on the causes of SATNet's failure andhow to prevent them.

Assessing SATNet's Ability to Solve the Symbol Grounding Problem