Symbolic learning enables self-evolving agents

Chapter 9 - Symbolic Learning

In recent years, Marxist theories have challenged the traditional, meritocratic perspective dominant in the sociology of education. The meritocracy assumes that schools, like the larger society, are based on the premise of equal opportunity; success in school is the result of hard work and good grades, which lead to good jobs and good incomes. Bowles and Gintis, among other revisionists, disagree arguing that the structure of education, sorting students into segregated, hierarchical curriculum tracks, mirrors the structure of the capitalist workplace and reproduces the existing class system such that the most advantaged persons and groups continue to fare well while the disadvantaged continue to fare poorly. This research tests some of the propositions of the Marxist-oriented correspondence principle of Bowles and Gintis. Previous research shows that the vocational track stresses such behaviors as submission to authority and dependability and does little to prepare students for college--characteristics highly suitable for manual class occupations. The academic track prepares students for higher education and emphasizes independent and symbolic learning--skills required of mental class jobs. Studies also show that minorities and working class students are over-represented in the vocational track whereas middle class students are over-represented in the academic track. Using a national sample of women seven years after high school, results of log-linear logit analysis indicate that tracking facilitates reproduction of a dichotomous categorization of class. For the manual class, reproduction is enhanced by student's participation in the vocational education track. In the mental class, however, reproduction is largely a consequence of being in the academic program. Other variables known to affect women's occupational position also vary by track. Women in the vocational track are more likely to have children, less likely to be single, have lower self-esteem, have traditional sex role attitudes, and less likely to achieve higher education than women from the academic track. Though social mobility occurs, hypotheses drawn from the correspondence principle were supported.

Machine learning is at the center of mainstream technology and outperforms classical approaches to handcrafted feature design. Aside from its learning process for artificial feature extraction, it has an end-to-end paradigm from input to output, reaching outstandingly accurate results. However, security concerns about its robustness to malicious and imperceptible perturbations have drawn attention since its prediction can be changed entirely. Salient object detection is a research area where deep convolutional neural networks have proven effective but whose trustworthiness represents a significant issue requiring analysis and solutions to hackers’ attacks. Brain programming is a kind of symbolic learning in the vein of good old-fashioned artificial intelligence. This work provides evidence that symbolic learning robustness is crucial in designing reliable visual attention systems since it can withstand even the most intense perturbations. We test this evolutionary computation methodology against several adversarial attacks and noise perturbations using standard databases and a real-world problem of a shorebird called the Snowy Plover portraying a visual attention task. We compare our methodology with five different deep learning approaches, proving that they do not match the symbolic paradigm regarding robustness. All neural networks suffer significant performance losses, while brain programming stands its ground and remains unaffected. Also, by studying the Snowy Plover, we remark on the importance of security in surveillance activities regarding wildlife protection and conservation.

This review paper explores the integration of neuro-symbolic reasoning and deep learning within autonomous robotics, proposing a novel framework to enhance decision-making processes in dynamic environments. The paper begins by examining the challenges AI models face, particularly in context-aware decision-making, and highlights the limitations of existing approaches. It then presents a conceptual model that synergizes the interpretability of symbolic reasoning with the perceptual power of deep learning. This integrated framework is designed to improve real-time contextual understanding, decision-making under uncertainty, and adaptability. The paper also discusses the potential impact of this framework across various industries, such as autonomous vehicles, drones, and healthcare robotics, while outlining future research directions to refine and scale the proposed model. Through this review, the paper aims to contribute to advancing autonomous systems by providing a more robust and interpretable approach to AI-driven decision-making. Keywords: Neuro-Symbolic Integration, Autonomous Robotics, Deep Learning, Symbolic Reasoning, Decision-Making, Symbolic Learning.

Symbolic learning

This paper describes RAPTURE—a system for revising probabilistic knowledge bases that combines connectionist and symbolic learning methods. RAPTURE uses a modified version of backpropagation to ref...

Deep learning and symbolic learning are two frequently employed methods in Sequential Recommendation (SR). Recent neural-symbolic SR models demonstrate their potential to enable SR to be equipped with concurrent perception and cognition capacities. However, neural-symbolic SR remains a challenging problem due to open issues like representing users and items in logical reasoning. In this paper, we combine the Deep Neural Network (DNN) SR models with logical reasoning and propose a general framework named Sequential Recommendation with Probabilistic Logical Reasoning (short for SR-PLR). This framework allows SR-PLR to benefit from both similarity matching and logical reasoning by disentangling feature embedding and logic embedding in the DNN and probabilistic logic network. To better capture the uncertainty and evolution of user tastes, SR-PLR embeds users and items with a probabilistic method and conducts probabilistic logical reasoning on users' interaction patterns. Then the feature and logic representations learned from the DNN and logic network are concatenated to make the prediction. Finally, experiments on various sequential recommendation models demonstrate the effectiveness of the SR-PLR. Our code is available at https://github.com/Huanhuaneryuan/SR-PLR.

Limiting CoP’s learning to the functional dimension contrasts with ‘learning to be a member’ foregrounded in early CoPs research. This paper proposes a cultural perspective to study CoPs which allows to consider both symbolic and functional aspects in learning while also interrogating the role of learning to be communal, i.e. learning to take part of any community and the abilities it requires. Observing the community life of two inter-organizational CoPs (financial analysts and physicians), we examine the role of totems and rituals, providing a complimentary understanding of CoPs dynamics . We offer suggestions to further develop the cultural approach in CoPs studies and identify practical and managerial implications, including higher participation.

Computational Intelligence is a relatively new branch of science which, to some extent, can be regarded as a successor of “traditional” Artificial Intelligence. Unlike AI, which relies on symbolic learning and heuristic approaches to problem solving, CI mainly involves systems that are inspired from nature, such as (artificial) neural networks, evolutionary computation, fuzzy systems, chaos theory, probabilistic methods, swarm intelligence, ant systems, and artificial immune systems. In a wider perspective CI includes also part of machine learning, in particular the reinforcement learning methods. Applying either one or a combination of the above-mentioned disciplines allows implementation of the elements of learning and adaptation in the proposed solutions which make such systems somehow intelligent. In the game playing domain the most popular CI disciplines are neural networks, evolutionary and neuro-evolutionary methods, and reinforcement learning. These domains are briefly introduced in the remainder of this chapter along with sample game-related applications. The focus of the presentation is on the aspects of learning and autonomous development. Relevant literature is provided for possible further reading.

The fourth edition of this bestselling textbook explains the principles of artificial intelligence (AI) and its practical applications. Using clear and concise language, it provides a solid grounding across the full spectrum of AI techniques, so that its readers can implement systems in their own domain of interest. The coverage includes knowledge-based intelligence, computational intelligence (including machine learning), and practical systems that use a combination of techniques. All the key techniques of AI are explained—including rule-based systems, Bayesian updating, certainty theory, fuzzy logic (types 1 and 2), agents, objects, frames, symbolic learning, case-based reasoning, genetic algorithms and other optimization techniques, shallow and deep neural networks, hybrids, and the Lisp, Prolog, and Python programming languages. The book also describes a wide range of practical applications in interpretation and diagnosis, design and selection, planning, and control. Fully updated and revised, Intelligent Systems for Engineers and Scientists: A Practical Guide to Artificial Intelligence, Fourth Edition features: A new chapter on deep neural networks, reflecting the growth of machine learning as a key technique for AI A new section on the use of Python, which has become the de facto standard programming language for many aspects of AI The rule-based and uncertainty-based examples in the book are compatible with the Flex toolkit by Logic Programming Associates (LPA) and its Flint extension for handling uncertainty and fuzzy logic. Readers of the book can download this commercial software for use free of charge. This resource and many others are available at the author’s website: adrianhopgood.com. Whether you are building your own intelligent systems, or you simply want to know more about them, this practical AI textbook provides you with detailed and up-to-date guidance.

The field of 'DNA linguistics' has emerged from pioneering work in computational linguistics and molecular biology. Most formal grammars in this field are expressed using Definite Clause Grammars but these have computational limitations which must be overcome. The present study provides a new DNA parsing system, comprising a logic grammar formalism called Basic Gene Grammars and a bidirectional chart parser DNA-ChartParser. The use of Basic Gene Grammars is demonstrated in representing many formulations of the knowledge of Escherichia coli promoters, including knowledge acquired from human experts, consensus sequences, statistics (weight matrices), symbolic learning, and neural network learning. The DNA-ChartParser provides bidirectional parsing facilities for BGGs in handling overlapping categories, gap categories, approximate pattern matching, and constraints. Basic Gene Grammars and the DNA-ChartParser allowed different sources of knowledge for recognizing E.coli promoters to be combined to achieve better accuracy as assessed by parsing these DNA sequences in real-world data sets.

Symbolic Learning

Organizations, as any complex and inherently distributed entities, are characterized by their internal and external interactions. Generally, and as a result of the continuous interactive process, the involved organizations become more efficient This performance increase, achieved through resources optimization, can be seen as the outcome of a know-how acquired from previous interactions.In broad terms, the work presented in this paper can be classified as a contribution to the study and modeling of the behavior of organizations. In particular, we are concerned with a specific inter-organization relation: the selection process that leads to the establishment of contracts between organizations. This selection process can be characterized as an iterative loop composed of an evaluation phase followed by a negotiation phase. During the selection activity, conflicts may occur imposing further negotiation as a mean for conflict resolution. According to the diverse selection methodologies that can be adopted, different learning opportunities can also be detected.The computational system under development, which supports the above mentioned interaction processes, is called ARTOR (ARTificial ORganizations), and is based on the Distributed Artificial Intelligence — Multi-Agent Systems (DAI-MAS) and Symbolic Learning (SL) paradigms. Each component, or agent, is provided with the needed observation, planning, coordination, execution, communication and learning capabilities to perform its social role.KeywordsDistributed AIOrganizations Integration and ModelingDistributed Learning

This paper addresses the problem of incorporating prior knowledge into learning algorithms. An impressive variety of hand-crafted methods dealing with this difficult problem has been elaborated by both symbolic machine learning and neural networks communities. However, no fairly general methodology has emerged yet. The contribution of this paper is two-folded. First, we propose a Bayesian view of domain knowledge incorporation. In our framework the learning algorithm’s designer is proposed to express available prior knowledge in terms of mixture distributions on both parameters and models envolved into a given type of learning. Then the known Bayesian learning machinery is put into work. Second, we fulfill a detailled case study applying our framework to extract logical rules from neural networks. We analyse our approach doing computational experiments on the difficult problem of protein secondary structure prediction. Besides, for this problem, we propose a Dirichlet mixture modeling of training data.

Discusses various avenues for exploiting biological learning mechanisms within machine learning. Special attention is given to the following issues: (a) the reasons for the wide variety of biological learning mechanisms; (b) the relation between lifetime and genetic learning; (c) a description of the driving forces of genetic learning and their use in evolutionary computation. Various symbolic machine learning and reasoning techniques can be used to complement (genetic and/or neural) sub-symbolic learning. A first approach uses symbolic induction for explaining the behavior of (genetically evolved) neural nets. Next, a general framework for the use of (symbolic) domain knowledge during genetic learning is introduced.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>