Deep nets have done well with early adopters, but the future will soon depend on crossing the chasm. The goal of this paper is to make deep nets more accessible to a broader audience including people with little or no programming skills, and people with little interest in training new models. A github is provided with simple implementations of image classification, optical character recognition, sentiment analysis, named entity recognition, question answering (QA/SQuAD), machine translation, speech to text (SST), and speech recognition (STT). The emphasis is on instant gratification. Non-programmers should be able to install these programs and use them in 15 minutes or less (per program). Programs are short (10–100 lines each) and readable by users with modest programming skills. Much of the complexity is hidden behind abstractions such as pipelines and auto classes, and pretrained models and datasets provided by hubs: PaddleHub, PaddleNLP, HuggingFaceHub, and Fairseq. Hubs have different priorities than research. Research is training models from corpora and fine-tuning them for tasks. Users are already overwhelmed with an embarrassment of riches (13k models and 1k datasets). Do they want more? We believe the broader market is more interested in inference (how to run pretrained models on novel inputs) and less interested in training (how to create even more models).

FOLD-RM is an automated inductive learning algorithm for learning default rules for mixed (numerical and categorical) data. It generates an (explainable) answer set programming (ASP) rule set for multi-category classification tasks while maintaining efficiency and scalability. The FOLD-RM algorithm is competitive in performance with the widely used, state-of-the-art algorithms such as XGBoost and multi-layer perceptrons, however, unlike these algorithms, the FOLD-RM algorithm produces an explainable model. FOLD-RM outperforms XGBoost on some datasets, particularly large ones. FOLD-RM also provides human-friendly explanations for predictions.

Both logic programming in general and Prolog in particular have a long and fascinating history, intermingled with that of many disciplines they inherited from or catalyzed. A large body of research has been gathered over the last 50 years, supported by many Prolog implementations. Many implementations are still actively developed, while new ones keep appearing. Often, the features added by different systems were motivated by the interdisciplinary needs of programmers and implementors, yielding systems that, while sharing the “classic” core language, in particular, the main aspects of the ISO-Prolog standard, also depart from each other in other aspects. This obviously poses challenges for code portability. The field has also inspired many related, but quite different languages that have created their own communities. This article aims at integrating and applying the main lessons learned in the process of evolution of Prolog. It is structured into three major parts. First, we overview the evolution of Prolog systems and the community approximately up to the ISO standard, considering both the main historic developments and the motivations behind several Prolog implementations, as well as other logic programming languages influenced by Prolog. Then, we discuss the Prolog implementations that are most active after the appearance of the standard: their visions, goals, commonalities, and incompatibilities. Finally, we perform a SWOT analysis in order to better identify the potential of Prolog and propose future directions along with which Prolog might continue to add useful features, interfaces, libraries, and tools, while at the same time improving compatibility between implementations.

We condense the theory of UTxO blockchains down to a simple and compact set of four type equations (Idealised EUTxO), and to an algebraic characterisation (abstract chunk systems), and exhibit an adjoint pair of functors between them. This gives a novel account of the essential mathematical structures underlying blockchain technology, such as Bitcoin.

In this paper, we propose a sparse point-plane odometry used in structured environments. Compared to a point-based odometry, we add additional planar constraints into the process of optimization, making the results more reliable. A novel grid-based plane detection algorithm is proposed to cluster sparse points in the same planes. Then, the planes are parameterized by inverse normal and take part in the windowed optimization. By reducing the size of Hessian Matrix, the process of optimization converges faster. Compared to the original point-based odometry, the proposed method performs better on both robustness and efficiency in structured environments.

The realizing of variable output constant force has received wide attention. To achieve a force regulation in an economic way, a configuration of the constant force mechanism (CFM) referring to positive and negative stiffness combination method is proposed in this paper. By adjusting preloading displacement applied on positive-stiffness structure of the CFM, the variable constant force output can be realized. The force–displacement expression of the CFM in the non-preloaded condition is deduced by the established analytical models. Furthermore, parametric sensitivity analysis with several architectural parameters are conducted for optimizing physical structures. Finally, the correctness of the proposed principle is verified by experimental studies. The observed experimental results show that the CFM under different preloading displacements can provide required output constant force, which is consistent with proposed hypothesis.