Logical Neural Networks (LNNs) are a type of architecture which combine a neural network's abilities to learn and systems of formal logic's abilities to perform symbolic reasoning. LLNs provide programmers the ability to implicitly modify the underlying structure of the neural network via logical formulae. In this paper, we take advantage of this abstraction to extend LNNs to support equality and function symbols via first-order theories. This extension improves the power of LNNs by significantly increasing the types of problems they can tackle. As a proof of concept, we add support for the first-order theory of equality to IBM's LNN library and demonstrate how the introduction of this allows the LNN library to now reason about expressions without needing to make the unique-names assumption.

Art lovers usually have to rely on headsets or humans to guide them around galleries. But visitors to the Art Gallery of Western Australia in Perth can now take a tour in the company of a little robot called Aggie. Like many galleries, it is dealing with a lack of money and falling visitor numbers. So, the curators are taking a less conventional route to attract more visitors. "We thought it would be really fun for family audiences to have something which was almost like a child-like guide, but a robot, who could excite them and also create new worlds around them," Chris Taverns, from the Art Gallery of Western Australia, told Al Jazeera.

The writing is on the LED screen: our jobs are ours for as long as the robots don't want them. But no one could have predicted they'd come for the gallery guides first. The world's first humanoid robot has started taking tours at the Art Gallery of Western Australia (AGWA) – two a month, for now. It seems a cruel twist of fate to have art history graduates among the first to be made redundant by robots; they have a hard enough time finding work as it is. But when I travel to AGWA to meet the future of work, it is plugged into the wall, charging.