Chapter 1. Neural-Symbolic Learning and Reasoning: A Survey and Interpretation1

The study and understanding of human behaviour is relevant to computer science, artificial intelligence, neural computation, cognitive science, philosophy, psychology, and several other areas. Presupposing cognition as basis of behaviour, among the most prominent tools in the modelling of behaviour are computational-logic systems, connectionist models of cognition, and models of uncertainty. Recent studies in cognitive science, artificial intelligence, and psychology have produced a number of cognitive models of reasoning, learning, and language that are underpinned by computation. In addition, efforts in computer science research have led to the development of cognitive computational systems integrating machine learning and automated reasoning. Such systems have shown promise in a range of applications, including computational biology, fault diagnosis, training and assessment in simulators, and software verification. This joint survey reviews the personal ideas and views of several researchers on neural-symbolic learning and reasoning. The article is organised in three parts: Firstly, we frame the scope and goals of neural-symbolic computation and have a look at the theoretical foundations. We then proceed to describe the realisations of neural-symbolic computation, systems, and applications. Finally we present the challenges facing the area and avenues for further research.

Abductive Knowledge Induction from Raw Data

For many reasoning-heavy tasks with raw inputs, it is challenging to design an appropriate end-to-end pipeline to formulate the problem-solving process. Some modern AI systems, e.g., Neuro-Symbolic Learning, divide the pipeline into sub-symbolic perception and symbolic reasoning, trying to utilise data-driven machine learning and knowledge-driven problem-solving simultaneously. However, these systems suffer from the exponential computational complexity caused by the interface between the two components, where the sub-symbolic learning model lacks direct supervision, and the symbolic model lacks accurate input facts. Hence, they usually focus on learning the sub-symbolic model with a complete symbolic knowledge base while avoiding a crucial problem: where does the knowledge come from? In this paper, we present Abductive Meta-Interpretive Learning (MetaAbd) that unites abduction and induction to learn neural networks and logic theories jointly from raw data. Experimental results demonstrate that MetaAbd not only outperforms the compared systems in predictive accuracy and data efficiency but also induces logic programs that can be re-used as background knowledge in subsequent learning tasks. To the best of our knowledge, MetaAbd is the first system that can jointly learn neural networks from scratch and induce recursive first-order logic theories with predicate invention.

Logic-based Robotics

This chapter explores methods for combining symbolic and sub-symbolic reasoning and learning systems to take advantage of the strengths of each approach in challenging tasks in robotics. In perception, Inductive Logic Programming (ILP) can be used to learn descriptions of classes of objects and to find relations between objects. Examples are given of perception for robots in urban search and rescue. We also describe systems for learning plans and behaviours for robots. Relational learning is used to acquire abstract model of robot actions that are then used to constrain sub-symbolic learning for low-level control. Models can be variously expressed in the classical STRIPS representation or as qualitative models. A STRIPS-like model is acquired by a robot that learns to use tools and also designs new tools. A qualitative model is constructed by a robot that learns to traverse uneven terrain in urban search and rescue. The model is refined by reinforcement learning.

Efektivitas Model Pembelajaran Simbolik Pada Perkuliahan Agama Kristen dalam Menginternalisasikan Nilai-Nilai Iman dan Moral

The using of learning model determines learning outcomes. The symbolic learning model is a way to improve Christian lectures internalize the values of faith and moral so that it can contribute namely to form a human person with nobel character. What kinds of learning model is effective? The learning model in certain material is not effective in other material. Based on the problem and the formulation of the problem, the objectives of the study: First, to design and test it out the symbolic learning model in Christian Lectures. Second, to find out and to reveal the effectiveness the symbolic learning model in internalizing the values of faith and moral in Christian lectures. The characteristic of this research to solve the problem that being faced and make the condition better by action which is refined continuously. Researchers reflection found out the source of the problem is not in accordance. The researcher will be tested it out a alternative model by doing the model symbolic learning in Christian lectures. The discovery will contribute in national education in overcoming the gap between attain a level of understanding and character development. The research used the spiral model Kemmis and Taggart that will emphasize the reflection spiral. It self consist of planning, action, observation, reflection and replanning. The research was done with two circles. The result of the reflection and first circle recommendation determine needs and the activities of second circle. The data collection will be done by interview, observation, documentation and questionnaire. So, will be analyzed be by reduced, on display and conclusion. The data was analyzed quantitatively by formula: I = X 100% (Internalization of values : total value = total college students x 100). The result of the research that the using of learning model symbol based in Christian education lectures can be used to achieve the values of faith and moral and stimulate the college student to build commitment embodiment of values in life.Penggunaan model pembelajaran menentukan hasil belajar. Model pembelajaran simbolik sebagai jalan untuk mengembangkan perkuliahan Agama Kristen dengan menginternalisasikan nilai-nilai iman dan moral, sehingga dapat berkontribusi pada pencapaian tujuan Pendidikan Nasional yakni membentuk pribadi manusia yang berakhlak mulia. Apakah model pembelajaran simbolik efektif untuk menginternalisasi nilai iman dan moral mahasiswa? Berdasarkan masalah dan rumusan masalah penelitian ini bertujuan Pertama; untuk mendesain dan mengujicobakan model pembelajaran simbolik dalam perkuliahan Agama. Kedua; untuk menemukan dan mengungkapkan efektivitas model pembelajaran simbolik dalam menginternalisasikan nilai-nilai iman dan moral dalam perkuliahan Agama Kristen. Sifat khas penelitan ini adalah untuk mengatasi masalah yang sedang dihadapi dan membuat kondisi lebih baik dengan tindakan yang disempurnakan secara terus-menerus. Refleksi peneliti menemukan sumber persoalan pada model pembelajaran yang tidak sesuai. Peneliti akan mengujicobakan suatu model alternatif, yakni model pembelajaran simbolik pada PAK, untuk menemukan efektivitas dari model ini. Penemuan akan berkontribusi pada dunia pendidikan dalam mengatasi jurang antara pencapaian tingkat pemahaman dengan pengembangan karakter. Penelitian menggunakan model spiral Kemmis dan Taggart yang akan menekankan spiral refleksi diri yang terdiri dari perencanaan, tindakan, orservasi, dan refleksi dan perencanaan kembali sebagai untuk memahami apa yang seharusnya di buat untuk mengembangkan situasi pendidikan. Penelitian dilakukan dengan dua siklus. Hasil refleksi dan rekomendasi siklus pertama menentukan kebutuhan dan kegiatan siklus kedua. Pengumpulan data akan dilakukan lewat wawancara, pengamatan, dokumentasi, dan angket. Maka dianalisis dengan cara direduksi, didisplay, disimpulkan. Data angket akan dianalisis secara kuantitatif dengan rumus I = X 100% (Internalisasi nilai = jumlah nilai: Jumlah Mahasiswa x 100). Hasil penelitian bahwa penggunaan model pembelajaran berbasis simbol dalam perkuliahan Pendidikan Agama Kristen dapat digunakan untuk mencapai iman dan moral serta merangsang mahasiswa untuk membangun komitmen perwujudan nilai-nilai dalam kehidupan.