collaborators

5 papers

cs.LG2025

Exploring possible vector systems for faster training of neural networks with preconfigured latent spaces

Nikita Gabdullin

The overall neural network (NN) performance is closely related to the properties of its embedding distribution in latent space (LS). It has recently been shown that predefined vect…

cs.LG2025

Using predefined vector systems as latent space configuration for neural network supervised training on data with arbitrarily large number of classes

Nikita Gabdullin

Supervised learning (SL) methods are indispensable for neural network (NN) training used to perform classification tasks. While resulting in very high accuracy, SL training often r…

cs.LG2025

The effects of Hessian eigenvalue spectral density type on the applicability of Hessian analysis to generalization capability assessment of neural networks

Nikita Gabdullin

Hessians of neural network (NN) contain essential information about the curvature of NN loss landscapes which can be used to estimate NN generalization capabilities. We have previo…

cs.CV2024

Improving analytical color and texture similarity estimation methods for dataset-agnostic person reidentification

Nikita Gabdullin

This paper studies a combined person reidentification (re-id) method that uses human parsing, analytical feature extraction and similarity estimation schemes. One of its prominent…

cs.LG2024

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis

Nikita Gabdullin

This paper studies generalization capabilities of neural networks (NNs) using new and improved PyTorch library Loss Landscape Analysis (LLA). LLA facilitates visualization and anal…