Neurules and connectionist expert systems: Unexplored neuro-symbolic reasoning aspects

Neuro-symbolic approaches combine neural and symbolic methods. This paper explores aspects regarding the reasoning mechanisms of two neuro-symbolic approaches, that is, neurules and connectionist expert systems. Both provide reasoning and explanation facilities. Neurules are a type of neuro-symbolic rules tightly integrating the neural and symbolic components, giving pre-eminence to the symbolic component. Connectionist expert systems give pre-eminence to the connectionist component. This paper explores reasoning aspects about neurules and connectionist expert systems that have not been previously addressed. As far as neurules are concerned, an aspect playing a role in conflict resolution (i.e., order of neurules) is explored. Experimental results show an improvement in reasoning efficiency. As far as connectionist expert systems are concerned, variations of the reasoning mechanism are explored. Experimental results are presented for them as well showing that one of the variations generally performs better than the others.

Neuro-symbolic artificial intelligence

Neuro-Symbolic Artificial Intelligence – the combination of symbolic methods with methods that are based on artificial neural networks – has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is meant to serve as a convenient starting point for research on the general topic.

Approximate Inference for Neural Probabilistic Logic Programming

DeepProbLog is a neural-symbolic framework that integrates probabilistic logic programming and neural networks. It is realized by providing an interface between the probabilistic logic and the neural networks. Inference in probabilistic neural symbolic methods is hard, since it combines logical theorem proving with probabilistic inference and neural network evaluation. In this work, we make the inference more efficient by extending an approximate inference algorithm from the field of statistical-relational AI. Instead of considering all possible proofs for a certain query, the system searches for the best proof. However, training a DeepProbLog model using approximate inference introduces additional challenges, as the best proof is unknown at the start of training which can lead to convergence towards a local optimum. To be able to apply DeepProbLog on larger tasks, we propose: 1) a method for approximate inference using an A*-like search, called DPLA* 2) an exploration strategy for proving in a neural-symbolic setting, and 3) a parametric heuristic to guide the proof search. We empirically evaluate the performance and scalability of the new approach, and also compare the resulting approach to other neural-symbolic systems. The experiments show that DPLA* achieves a speed up of up to 2-3 orders of magnitude in some cases.

Meira Paibis Movement Roles in Creating Peace at Northeastern India

Starting from the aim of stopping the rebel movement, the enactment of the Armed Forces Special Powers Act (AFSPA) of 1958 in practice became a boomerang for security stability in Northeastern India. The privileges granted by the government to soldiers are used as a pretext for discrimination and violations of human rights. The patriarchal tradition, which then considers women as property and weak creatures, causes women and children to suffer the most. Reports of sexual harassment cases, rape, and even murder unilaterally encouraged Meira Paibis as a grassroots women's movement to develop a strategy of resistance. Meira Paibis uses a non-violent approach through symbolic methods that are viewed as extreme and controversial in its mission. This research will describe the significant role of the Meira Paibis women's movement in organizing resistance to AFSPA policies and their efforts to achieve positive peace in Northeastern India. This paper will elaborate on the non-violence approach to see the strategies played by Meira Paibis and the obstacles faced in the process of achieving her goals.

POSISI PEREMPUAN DALAM INJIL LUKAS: Sebuah Kajian dengan Perspektif Honor and Shame Melalui Kisah Elisabet

The number of female figures who appear in Luke's gospel behind a social context that places women in a lower position than men, raises questions about the position of women in Luke's gospel. This article aims to explore the woman in Luke's gospel through the story of Elizabeth. Because the issue of women's position related to social status, the analysis in this study will be based on the perspective of honor and shame with symbolic methods in cultural anthropology as the methodology. The results of this analysis show a positive and significant position for women in the Gospel of Luke. This is shown through the symbols of honor embedded in Elizabeth, as well as her significant and prominent role. Even Elizabeth is shown to be in a much more positive position than her husband, Zacharias. Elizabeth shows that women, like men, can play an important role as patrons, witnesses, and prophets. The way Luke positions Elizabeth indicates that there is an elevation of honor for women to an equal position with men. Keywords: honor and shame, cultural anthropology, Elizabeth, women’s position, the Gospel of Luke Abstrak: Banyaknya tokoh perempuan yang dimunculkan di Injil Lukas di balik konteks sosial yang menempatkan perempuan pada posisi yang lebih rendah daripada laki-laki, menimbulkan pertanyaan mengenai posisi perempuan dalam Injil Lukas. Artikel ini bertujuan untuk mengeksplorasi posisi perempuan dalam Injil Lukas melalui kisah Elisabet. Mengingat isu tentang posisi perempuan berhubungan dengan status sosial, maka analisis dalam penelitian ini akan didasarkan pada perspektif honor and shame dengan metode simbolik dalam antropologi budaya sebagai metodologinya. Hasil dari analisis ini memperlihatkan posisi yang positif dan signifikan bagi perempuan dalam Injil Lukas. Hal ini diperlihatkan melalui simbol-simbol kehormatan yang disematkan kepada Elisabet, serta perannya yang terlihat signifikan dan menonjol. Bahkan Elisabet diperlihatkan pada posisi yang jauh lebih positif daripada Zakharia, suaminya. Elisabet memperlihatkan bahwa perempuan, seperti juga laki-laki, dapat berperan penting sebagai patron, saksi, dan penyampai nubuat. Cara Lukas memosisikan Elisabet ini mengindikasikan adanya pengangkatan kehormatan perempuan pada posisi yang setara dengan laki-laki. Kata-kata Kunci: honor and shame, antropologi budaya, Elisabet, posisi perempuan, Injil Lukas.

Modeling Content and Context with Deep Relational Learning

Building models for realistic natural language tasks requires dealing with long texts and accounting for complicated structural dependencies. Neural-symbolic representations have emerged as a way to combine the reasoning capabilities of symbolic methods, with the expressiveness of neural networks. However, most of the existing frameworks for combining neural and symbolic representations have been designed for classic relational learning tasks that work over a universe of symbolic entities and relations. In this paper, we present DRaiL, an open-source declarative framework for specifying deep relational models, designed to support a variety of NLP scenarios. Our framework supports easy integration with expressive language encoders, and provides an interface to study the interactions between representation, inference and learning.