Wyniki wyszukiwania - BazTech

1

Dynamic semantic description and search methods for heterogeneous learning resources

Lai Xiaocong, Pan Ying, Jiang Xueling

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2022

|

Vol. 70, nr 3

art. no. e139434

EN

Learning resources are massive, heterogeneous, and constantly changing. How to find the required resources quickly and accurately has become a very challenging work in the management and sharing of learning resources. According to the characteristics of learning resources, this paper proposes a progressive learning resource description model, which can describe dynamic heterogeneous resource information on a fine-grained level by using information extraction technology, then a semantic annotation algorithm is defined to calculate the semantic of learning resource and add these semantic to the description model. Moreover, a semantic search method is proposed to find the required resources, which calculate the content with the highest similarity to the user query, and then return the results in descending order of similarity. The simulation results show that the method is feasible and effective.

2

Usage of deep learning in recent applications

Dubey A.

Archives of Materials Science and Engineering

|

2022

|

Vol. 115, nr 2

49--57

EN

Purpose: Deep learning is a predominant branch in machine learning, which is inspired by the operation of the human biological brain in processing information and capturing insights. Machine learning evolved to deep learning, which helps to reduce the involvement of an expert. In machine learning, the performance depends on what the expert extracts manner features, but deep neural networks are self-capable for extracting features. Design/methodology/approach: Deep learning performs well with a large amount of data than traditional machine learning algorithms, and also deep neural networks can give better results with different kinds of unstructured data. Findings: Deep learning is an inevitable approach in real-world applications such as computer vision where information from the visual world is extracted, in the field of natural language processing involving analyzing and understanding human languages in its meaningful way, in the medical area for diagnosing and detection, in the forecasting of weather and other natural processes, in field of cybersecurity to provide a continuous functioning for computer systems and network from attack or harm, in field of navigation and so on. Practical implications: Due to these advantages, deep learning algorithms are applied to a variety of complex tasks. With the help of deep learning, the tasks that had been said as unachievable can be solved. Originality/value: This paper describes the brief study of the real-world application problems domain with deep learning solutions.

3

Exploring MiZAR library with MML Query

Bancerek G.

Zeszyty Naukowe Politechniki Białostockiej. Informatyka

|

2007

|

Z. 2

5-18

EN

MiZAR, a proof-checking system, is used to build the MiZAR Mathematical Li-brary (MML). MML Query is a semantics-based tool for managing the mathematical knowl-edge in MiZAR including searching, browsing and presentation of the evolving MML content. The tool is becoming widely used as an aid for MiZAR authors and plays an essential role in the ongoing reorganization of MML. In the paper, we briefly present MiZAR system including language, tools for logical verifi-cation and publishing, foundations of MML, its content and maintenance, and the problems raising when using the MML (information retrieval and rendering). We also present the pos-sibilities offered by MML Query to solve these problems.

PL

MlZAR(komputerowy system weryfikacji dowodów) jest używany do budowania MiZAR Mathematical Library (MML). MML Query jest narzędziem opartym o semantykę tekstu mizarowego służącym do zarządzania wiedzą w systemie MiZAR włączając w to wyszukiwanie, przeglądanie i prezentację ewolującej zawartości MML. Narzędzie to stało się szeroko używane jako pomoc dla autorów mizarowych oraz odgrywa istotną rolę w nieustających reorganizacjach MML. W artykule zaprezentowane są elementy systemu MiZAR i MML Query jak język, narzędzia logicznej weryfikacji i automatycznej publikacji, podstawy biblioteki MML, jej zawartość i konserwacja oraz problemy pojawiające się przy używaniu MML (odzyskiwanie informacji orazjej przedstawianie). Ponadto, są przedstawione możliwości MMLQuery w rozwiązywaniu tych problemów.