Разработка аппаратного модуля классификации текстовых документов на базе ПЛИС
Are the main features of CAD software used in the development of equipment using FPGA. Is an example of job creation projects FPGA. Discusses some common problems and suggest ways to address them.
Provides an overview of the different ways to implement the high-speed I/O data to the PC using FPGA based on the use of commercially available modules. The possibility of developing a specialized unit that provides the present-simplification of the equipment.
Large-scale classification of text streams is an essential problem that is hard to solve. Batch processing systems are scalable and proved their effectiveness for machine learning but do not provide low latency. On the other hand, state-of-the-art distributed stream processing systems are able to achieve low latency but do not support the same level of fault tolerance and determinism. In this work, we discuss how the distributed streaming computational model and fault tolerance mechanisms can affect the correctness of text classification data flow. We also propose solutions that can mitigate the revealed pitfalls.
9th International Conference, AIST 2020, Skolkovo, Moscow, Russia, October 15–16, 2020, Revised Selected Papers
In this work realization of automatic scientific articles classification according to Universal Decimal Classifier is presented. Efficiency of neural networks technologies application for current task is researched, and optimal neural network structure and parameters are offered
The paper deals with the applicability of modern machine learning methods to the problem of automatic generation of UDC for scientific articles. As the classifiers, such models as artificial neural networks, logistic regression and boosting are considered. Graph algorithms and a prototype software module to generate UDC are designed.
The paper describes basic methods of data compression without loss and analyzes their advantages and disadvantages. There is a hardware implementation on FPGA of compression algorithm for stream processing of information. This algorithm can be used in applications related to telecommunications networks of distributed control systems.