Search

The Abstraction and Reasoning Corpus (ARC) is a general artificial intelligence benchmark that is currently unsolvable by any Machine Learning method, including Large Language Models (LLMs). It demands strong generalization and reasoning capabilities which are known to be weaknesses of Neural Network based systems. In this work, we propose a Program Synthesis system that uses Inductive Logic Programming (ILP), a branch of Symbolic AI, to solve ARC. We have manually defined a simple Domain Specific Language (DSL) that corresponds to a small set of object-centric abstractions relevant to ARC. This is the Background Knowledge used by ILP to create Logic Programs that provide reasoning capabilities to our system. The full system is capable of generalize to unseen tasks, since ILP can create Logic Program(s) from few examples, in the case of ARC: pairs of Input-Output grids examples for each task. These Logic Programs are able to generate Objects present in the Output grid and the combination of these can form a complete program that transforms an Input grid into an Output grid. We randomly chose some tasks from ARC that dont require more than the small number of the Object primitives we implemented and show that given only these, our system can solve tasks that require each, such different reasoning.

Here we define a new unification algorithm for terms interpreted in semantic domains denoted by a subclass of regular types here called deterministic regular types. This reflects our intention not to handle the semantic universe as a homogeneous collection of values, but instead, to partition it in a way that is similar to data types in programming languages. We first define the new unification algorithm which is based on constraint generation and constraint solving, and then prove its main properties: termination, soundness, and completeness with respect to the semantics. Finally, we discuss how to apply this algorithm to a dynamically typed version of Prolog., Comment: 19 pages

I use matched employer-employee records merged with corporate tax information from 2003 to 2017 to estimate labor market-wide effects of mergers and acquisitions in Brazil. Labor markets are defined by pairs of commuting zone and industry sector. In the following year of a merger, market size falls by 10.8%. The employment adjustment is concentrated in merging firms. For the firms not involved in M&As, I estimate a 1.07% decline in workers earnings and a positive, although not significant, increase in their size. Most mergers have a predicted impact of zero points in concentration, measured by the Herfindahl-Hirschman Index (HHI). I spillover firms, earnings decline similarly for mergers with high and low predicted changes in HHI. Contrary to the recent literature on market concentration in developed economies, I find no evidence of oligopsonistic behavior in Brazilian labor markets.

The semantic foundations for logic programming are usually separated into two different approaches. The operational semantics, which uses SLD-resolution, the proof method that computes answers in logic programming, and the declarative semantics, which sees logic programs as formulas and its semantics as models. Here, we define a new operational semantics called TSLD-resolution, which stands for Typed SLD-resolution, where we include a value "wrong", that corresponds to the detection of a type error at run-time. For this we define a new typed unification algorithm. Finally we prove the correctness of TSLD-resolution with respect to a typed declarative semantics., Comment: 17 pages

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, and, 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. Firstly, 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 which Prolog might continue to add useful features, interfaces, libraries, and tools, while at the same time improving compatibility between implementations., Comment: 87 pages, 2 figures. This article has been accepted for publication in Theory and Practice of Logic Programming (TPLP)

In this paper we present a new static data type inference algorithm for logic programming. Without the need of declaring types for predicates, our algorithm is able to automatically assign types to predicates which, in most cases, correspond to the data types processed by their intended meaning. The algorithm is also able to infer types given data type definitions similar to data definitions in Haskell and, in this case, the inferred types are more informative in general. We present the type inference algorithm, prove some properties and finally, we evaluate our approach on example programs that deal with different data structures., Comment: Pre-proceedings paper presented at the 31st International Symposium on Logic-Based Program Synthesis and Transformation (LOPSTR 2021), Tallinn, Estonia, and Virtual, September 7-8, 2021 (arXiv:2107.10160)

Application domains that require considering relationships among objects which have real-valued attributes are becoming even more important. In this paper we propose NeuralLog, a first-order logic language that is compiled to a neural network. The main goal of NeuralLog is to bridge logic programming and deep learning, allowing advances in both fields to be combined in order to obtain better machine learning models. The main advantages of NeuralLog are: to allow neural networks to be defined as logic programs; and to be able to handle numeric attributes and functions. We compared NeuralLog with two distinct systems that use first-order logic to build neural networks. We have also shown that NeuralLog can learn link prediction and classification tasks, using the same theory as the compared systems, achieving better results for the area under the ROC curve in four datasets: Cora and UWCSE for link prediction; and Yelp and PAKDD15 for classification; and comparable results for link prediction in the WordNet dataset., Comment: 14 pages

Types in logic programming have focused on conservative approximations of program semantics by regular types, on one hand, and on type systems based on a prescriptive semantics defined for typed programs, on the other. In this paper, we define a new semantics for logic programming, where programs evaluate to true, false, and to a new semantic value called wrong, corresponding to a run-time type error. We then have a type language with a separated semantics of types. Finally, we define a type system for logic programming and prove that it is semantically sound with respect to a semantic relation between programs and types where, if a program has a type, then its semantics is not wrong. Our work follows Milner's approach for typed functional languages where the semantics of programs is independent from the semantic of types, and the type system is proved to be sound with respect to a relation between both semantics., Comment: In Proceedings ICLP 2019, arXiv:1909.07646

There is a growing need for fast and accurate methods for testing developmental neurotoxicity across several chemical exposure sources. Current approaches, such as in vivo animal studies, and assays of animal and human primary cell cultures, suffer from challenges related to time, cost, and applicability to human physiology. We previously demonstrated success employing machine learning to predict developmental neurotoxicity using gene expression data collected from human 3D tissue models exposed to various compounds. The 3D model is biologically similar to developing neural structures, but its complexity necessitates extensive expertise and effort to employ. By instead focusing solely on constructing an assay of developmental neurotoxicity, we propose that a simpler 2D tissue model may prove sufficient. We thus compare the accuracy of predictive models trained on data from a 2D tissue model with those trained on data from a 3D tissue model, and find the 2D model to be substantially more accurate. Furthermore, we find the 2D model to be more robust under stringent gene set selection, whereas the 3D model suffers substantial accuracy degradation. While both approaches have advantages and disadvantages, we propose that our described 2D approach could be a valuable tool for decision makers when prioritizing neurotoxicity screening.