The imposition of hard constraints on the output of neural networks is a highly desirable
capability, as it instills confidence in AI by ensuring that neural network predictions adhere to …

In the ongoing quest for hybridizing discrete reasoning with neural nets, there is an
increasing interest in neural architectures that can learn how to solve discrete reasoning or …

Abstract The Sudoku Assistant app is an AI assistant that uses a combination of machine
learning and constraint programming techniques, to interpret and explain a pen-and-paper …

We introduce a curriculum learning framework for challenging tasks that require a
combination of pattern recognition and combinatorial reasoning, such as single-player …

We consider the problem of perception-based constraint solving, where part of the problem
specification is provided indirectly through an image provided by a user. As a pedagogical …

Probabilistic graphical models (PGMs) are tools for solving complex probabilistic
relationships. However, suboptimal PGM structures are primarily used in practice. This …

This work is devoted to the study of the features of functioning in Collaborative Human-AI
Decision-Making Systems with numerical channels. The system operates in automatic mode …

Artificial Neural Networks excel at identifying individual components in an image. However,
out-of-the-box, they do not manage to correctly integrate and interpret these components as …

Neural models and symbolic algorithms have recently been combined for tasks requiring
both perception and reasoning. Neural models ground perceptual input into a conceptual …

Increasingly, constraint programming problems can not be fully specified as facts, but part of
the problem input is predicted using machine learning; for example demand and price in …