Search

Artificial intelligence (AI) has permeated all human activities, bringing about significant changes and creating new scientific and ethical challenges. The field of education could not be an exception to this development. OpenAI's unveiling of ChatGPT, their large language model (LLM), has sparked significant interest in the potential applications of this technology in education. This paper aims to contribute to the ongoing discussion on the role of AI in education and its potential implications for the future of learning by exploring how LLMs could be utilized in the teaching of mathematics in higher education and how they compare to the currently widely used computer algebra systems (CAS) and other mathematical tools. It argues that these innovative tools have the potential to provide functional and pedagogical opportunities that may influence changes in curriculum and assessment approaches. [ABSTRACT FROM AUTHOR]

This paper presents RULES-5, a new induction algorithm for effectively handling problems involving continuous attributes. RULES-5 is a 'covering' algorithm that extracts IF–THEN rules from examples presented to it. The paper first reviews existing methods of rule extraction and dealing with continuous attributes. It then describes the techniques adopted for RULES-5 and gives a step-by-step example to illustrate their operation. The paper finally gives the results of applying RULES-5 and other algorithms to benchmark problems. These clearly show that RULES-5 generates rule sets that are more accurate than those produced by its immediate predecessor RULES-3 Plus and by a well-known commercially available divide-and-conquer machine learning algorithm. [ABSTRACT FROM AUTHOR]

Abstract: The fuzzy min–max (FMM) network is a supervised neural network classifier that forms hyperboxes for classification and prediction. In this paper, we propose modifications to FMM in an attempt to improve its classification performance when a small number of large hyperboxes are formed in the network. Given a new input pattern, in addition to measuring the fuzzy membership function of the input pattern to the hyperboxes formed in FMM, an Euclidean distance measure is introduced for predicting the target class associated with the new input pattern. A rule extraction algorithm is also embedded into the modified FMM network. A confidence factor is calculated for each FMM hyperbox, and a user-defined threshold is used to prune the hyperboxes with low confidence factors. Fuzzy if–then rules are then extracted from the pruned network. The benefits of the proposed modifications are twofold, viz., to improve the performance of FMM when large hyperboxes are formed in the network; to facilitate the extraction of a compact rule set from FMM to justify its predictions. To assess the effectiveness of modified FMM, two benchmark pattern classification problems are experimented, and the results from different methods published in the literature are compared. In addition, a fault detection and classification problem with a set of real sensor measurements collected from a power generation plant is evaluated using modified FMM. The results obtained are analyzed and explained, and implications of the modified FMM network as a useful fault detection and classification tool in real environments are discussed. [Copyright &y& Elsevier]

This paper aims at presenting the systems theory-based approach to the learning (instructional) process. Such as approach is necessary, if one takes into consideration the the complex and holistic nature of the learning process. The presented modeling is based on the definition of an automatic regulation system and artificial intelligence techniques. For this purpose, an Intelligent Instructional System (IIS) is defined using the concepts: inputs, outputs, perturbations factors, regulation, feedback and AI learning techniques. The contextual environment of learning plays the major role in this system and it establishes the perturbation factors. The regulation consists in AI learning techniques, so the IIS is a flexible and adaptive system. The process' behaviour is described using pseudo-boolean and linear equations. This kind of approach enables solving the problems of the complexity and uncertainty of the learning (instructional) systems and, particularly, those of the e-learning (online and offline). Applications of the proposed approach may be found in e-learning courses for Mathematics, Computing, Architecture, Archaeology, Cultural Heritage, etc. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a comparative analysis of different connectionist and statistical models for forecasting the weather of Vancouver, Canada. For developing the models, one year''s data comprising of daily temperature and wind speed were used. A multi-layered perceptron network (MLPN) and an Elman recurrent neural network (ERNN) were trained using the one-step-secant and Levenberg–Marquardt algorithm. Radial basis function network (RBFN) was employed as an alternative to examine its applicability for weather forecasting. To ensure the effectiveness of neurocomputing techniques, the connectionist models were trained and tested using different datasets. Moreover, ensembles of the neural networks were generated by combining the MLPN, ERNN and RBFN using arithmetic mean and weighted average methods. Subsequently, performance of the connectionist models and their ensembles were compared with a well-established statistical technique. Experimental results obtained have shown RBFN produced the most accurate forecast model compared to ERNN and MLPN. Overall, the proposed ensemble approach produced the most accurate forecast, while the statistical model was relatively less accurate for the weather forecasting problem considered. [Copyright &y& Elsevier]

In this paper we present a new approach to modeling finite set domain constraint problems using Reduced Ordered Binary Decision Diagrams (ROBDDs). We show that it is possible to construct an efficient set domain propagator which compactly represents many set domains and set constraints using ROBDDs. We demonstrate that the ROBDD-based approach provides unprecedented flexibility in modeling constraint satisfaction problems. leading to performance improvements. We also show that the ROBDD-based modeling approach can be extended to the modeling of integer and multiset constraint problems in straightforward manner. Since domain propagation is not always practical, we also show how to incorporate less strict consistency notions into the ROBDD framework, such as set bounds, cardinality bounds and lexicographic bounds consistency. Finally, we present experimental results that demonstrate the ROBDD-based solver performs better than various more conventional constraint solvers on several standard set constraint problems. [ABSTRACT FROM AUTHOR]

In character recognition, character contour is an important feature. Filtering processes using an n × n mask as a differentiation operator and the contour-following technique, among others are used for contour extraction. However, since numerous operations are required for such processes, these techniques require long processing time when a large number of images are to be processed. This paper describes a new method called double-threshold binarization (DTB), by which the contour of the character image can be extracted at high speed, without using filtering operations. The proposed method pays attention to the intensity gradient of the character image obtained as a gray-level image. The method can easily extract a character contour by using binarization and XOR operations with two different thresholds. A neural network is applied to determine these threshold values. As a practical evaluation of DTB, it is applied to hand-written zip code images with noise. We compare the contour extraction ability of DTB with the contour following method, the differentiation operator, the Sobel operator, and others. DTB proves to exhibit good quality of the extracted contour, noise robustness, and high speed of processing. In addition, we present an improved algorithm for the proposed method that achieves higher processing speed. The character contour can be extracted in a processing time that is 1/20 of that for conventional techniques. ©1998 Scripta Technica, Syst Comp Jpn, 29(13): 36–47, 1998 [ABSTRACT FROM AUTHOR]