Even though most interfaces in the real world are discrete, no efficient way exists to train neural networks to make use of them, yet. We enhance an Interaction Network (a Reinforcement Learning architecture) with discrete interfaces and train it on the generalized Dyck language. This task requires an understanding of hierarchical structures to solve, and has long proven difficult for neural networks. We provide the first solution based on learning to use discrete data structures. We encountered unexpected anomalous behavior during training, and utilized pre-training based on execution traces to overcome them. The resulting model is very small and fast, and generalizes to sequences that are an entire order of magnitude longer than the training data.

There is much excitement surrounding the field of brain-computer interfaces (BCI). Take, for example, recent headline-grabbing announcements from Neuralink, founded by Elon Musk, which has the long-term goal of helping to "secure humanity's future as a civilization relative to AI." Then, there is Facebook's development of wearable technology that hopes to achieve "hands-free communication without saying a word." While there are no guarantees that telepathy will ever exist, equally, there is no guarantee that it will not. Meanwhile, companies and organizations are making tremendous advancements and we can expect more effective and widespread use of BCIs as they become more sophisticated.

Answer set programming (ASP) is a successful declarative formalism for knowledge representation and reasoning. The evaluation of ASP programs is nowadays based on the Conflict-Driven Clause Learning (CDCL) backtracking search algorithm. Recent work suggested that the performance of CDCL-based implementations can be considerably improved on specific benchmarks by extending their solving capabilities with custom heuristics and propagators. However, embedding such algorithms into existing systems requires expert knowledge of the internals of ASP implementations. The development of effective solver extensions can be made easier by providing suitable programming interfaces. In this paper, we present the interface for extending the CDCL-based ASP solver WASP. The interface is both general, i.e. it can be used for providing either new branching heuristics and propagators, and external, i.e. the implementation of new algorithms requires no internal modifications of WASP. Moreover, we review the applications of the interface witnessing it can be successfully used to extend WASP for solving effectively hard instances of both real-world and synthetic problems. Under consideration in Theory and Practice of Logic Programming (TPLP).

The Vintage Computer Federation is the world's largest group of collectors and restorers of historic computing systems. Member activities include hands-on exhibitions conducted at all manner of tech-themed gatherings around the United States, in addition to the federation's own Vintage Computer Festival events. At the World Maker Faire in New York City, in October, two of our mid-Atlantic chapter members born in the 1970s decided to demonstrate computers and robotic kits from the 1980s, using programming languages developed in the 1960s. Charlie was built using the Capsela construction system. This system was first sold by the Mitsubishi Pencil Co. in Japan in 1975 and later licensed by toy manufacturers in other countries (and can now be found on eBay).