8 papers
Using predefined vector systems to speed up neural network multimillion class classification
Nikita Gabdullin, Ilya Androsov
Label prediction in neural networks (NNs) has O(n) complexity proportional to the number of classes. This holds true for classification using fully connected layers and cosine simi…
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…
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…
Latent space configuration for improved generalization in supervised autoencoder neural networks
Nikita Gabdullin
Autoencoders (AE) are simple yet powerful class of neural networks that compress data by projecting input into low-dimensional latent space (LS). Whereas LS is formed according to…
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…
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…