Scientific Seminar on the theme "Development of Conceptual Architecture for Improving the Efficiency of Information Search Systems on the Internet" was held at the Institute of Information Technology of ANAS.
Suleyman Suleymanzade, PhD student of the institute emphasized the relevance of the topic and noted that the use of in-depth training in search systems, machine learning and methods of intelligent analysis of texts is one of the innovative and perspective research directions.
He said that the search of information was related to the user's inquiry. The speaker noted that the use of in-depth training methods to offer solutions to address these problems was the main approach for researchers. He said that in-depth traning has a wide range of possibilities for successful application for providing relevance of information technology in the field of information search, automatic classification of texts, texts summarization, term weightning, text extraction , classification of inquiries, information filtering (spam filtration), automatic clustering of documents, analysis of links for web search , parallel processing, multilingual information search, semantic search, search of pictures and videos, and visualization of information search.
S.Suleymanzade noted that in the architecture offered to increase the efficiency of information search systems, deep neural networks like Convolutional Neural Network (CNN), Deep Neural Network (DNN), deep autoencoder are the main components of architecture.
At the end of the lecture, the views were exchanged, questions were answered. Head of department No2, PhD in technical sciences, associate professor Yadigar Imamverdiyev recommended to continue research in this direction.
© All rights reserved. Citing to www.ict.az is necessary upon using news