The article presents a novel local learning rule for spiking neural networks (SNNs). The
developed Supervised Learning method uses a combination of Hebbian rules, so-called …

This study explores the problem of limited context in Russian large language models (LLMs)
and proposes a new method for increasing their context size in an efficient manner. The …

When training fuzzy networks, they often face the problem of choosing a learning algorithm.
To solve the problem of choosing the most effective learning algorithm, various gradient and …

In this paper, the method for knowledge graph completion based on using multi-hop
reasoning is proposed. The relevance of the problem is due to the widespread use of large …

Recently, there has been essential progress in computer vision tasks such as classification,
detection, and segmentation. Point cloud registration algorithms align two or more different …

Point cloud registration is a central problem in many mapping and monitoring applications
such as 3D model reconstruction, computer vision, autonomous driving, and others. The …

The use of machine learning in pathognomy is being investigated to test the hypothesis
about the influence of classical music education on a person's face. A sample of images of …

The paper considers the problem of detecting distorted data using a multimodal approach.
Various methods of classification are being investigated. In the course of experimental …