No abstract

This study aims to create a classifier using machine learning methods that determine the psychological type of people based on the text published on social networks according to the Myers-Briggs Type Index classification. The article is based on the implementation of automation of the task of determining the personality type using machine learning, with an explanation for determining the characteristics of a person using the MBTI personality indicator. The methods of logistic regression, random forest and support vector machines were used, and a literary analysis of similar works was carried out. The article presents the progress of research work and the results of each classifier, as well as an analysis of the approaches used. In the context of the current quarantine restrictions, such studies can be of great help in the selection of personnel in companies due to the transition of people to an online format of work, since the study involves determining the personal qualities of people based on their posts in social networks. In this paper, the most effective machine learning algorithms for the Kazakh language, which are simple to use and do not require a lot of computing power, were used and, accordingly, the results of the work for each method were presented, among these methods, the accuracy and reliability of the classifier for the Kazakh language by the method of support vectors were at a good level.

No abstract

In recent years, some field programmable valve arrays (FPGAs) based on CNN release phase accelerators have been introduced. FPGA is widely used in portable devices. They can be programmed to achieve higher concurrency and provide better performance. The power consumption of the FPGA is lower than that of GPUs with the same workload. These reasons make the FPGA suitable for implementing the CNN release phase. They can provide relative output performance for GPUs and achieve low power consumption, which is very important for portable devices. To effectively implement the CNN output phase on the FPGA, the design should have high parallelism, and the hardware resources used should be minimized to reduce the area and power consumption. In the process of working with the help of a neural network, an algorithm for recognizing handwritten numbers is implemented. A special architecture is being created to implement a neural network at the appatent level. The performance during operation and power consumption is comparable to the performance of the processor and the GPU.

No abstract