Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Gabdullin, Nikita
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Exploring possible vector systems for faster training of neural networks with preconfigured latent spaces
por: Gabdullin, Nikita
Publicado: (2025)

Using predefined vector systems to speed up neural network multimillion class classification
por: Gabdullin, Nikita, et al.
Publicado: (2026)

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis
por: Gabdullin, Nikita
Publicado: (2024)

Latent space configuration for improved generalization in supervised autoencoder neural networks
por: Gabdullin, Nikita
Publicado: (2024)

The effects of Hessian eigenvalue spectral density type on the applicability of Hessian analysis to generalization capability assessment of neural networks
por: Gabdullin, Nikita
Publicado: (2025)

An attempt to generate new bridge types from latent space of generative adversarial network
por: Zhang, Hongjun
Publicado: (2024)

An approach based on class activation maps for investigating the effects of data augmentation on neural networks for image classification
por: Dorneles, Lucas M., et al.
Publicado: (2025)

Self-supervised Pre-training of Text Recognizers
por: Kišš, Martin, et al.
Publicado: (2024)

Comparing supervised learning dynamics: Deep neural networks match human data efficiency but show a generalisation lag
por: Huber, Lukas S., et al.
Publicado: (2024)

Image space formalism of convolutional neural networks for k-space interpolation
por: Dawood, Peter, et al.
Publicado: (2024)

SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning
por: Zhao, Shuai, et al.
Publicado: (2025)

An attempt to generate new bridge types from latent space of generative flow
por: Zhang, Hongjun
Publicado: (2024)

An attempt to generate new bridge types from latent space of PixelCNN
por: Zhang, Hongjun
Publicado: (2024)

An attempt to generate new bridge types from latent space of variational autoencoder
por: Zhang, Hongjun
Publicado: (2023)

Automated rock joint trace mapping using a supervised learning model trained on synthetic data generated by parametric modelling
por: Chiu, Jessica Ka Yi, et al.
Publicado: (2026)

Sign language recognition from skeletal data using graph and recurrent neural networks
por: Mederos, B., et al.
Publicado: (2025)

AI-based association analysis for medical imaging using latent-space geometric confounder correction
por: Liu, Xianjing, et al.
Publicado: (2023)

An attempt to generate new bridge types from latent space of denoising diffusion Implicit model
por: Zhang, Hongjun
Publicado: (2024)

Can neural networks count digit frequency?
por: Khandelwal, Padmaksh
Publicado: (2023)

Explaining latent representations of generative models with large multimodal models
por: Zhu, Mengdan, et al.
Publicado: (2024)

A foundation for exact binarized morphological neural networks
por: Aouad, Theodore, et al.
Publicado: (2024)

Kinematic analysis of structural mechanics based on convolutional neural network
por: Zhang, Leye, et al.
Publicado: (2024)

Learning Fourier shapes to probe the geometric world of deep neural networks
por: Wang, Jian, et al.
Publicado: (2025)

Referential communication in heterogeneous communities of pre-trained visual deep networks
por: Mahaut, Matéo, et al.
Publicado: (2023)

Wildlife Target Re-Identification Using Self-supervised Learning in Non-Urban Settings
por: Muthivhi, Mufhumudzi, et al.
Publicado: (2025)

Evaluating alignment between humans and neural network representations in image-based learning tasks
por: Demircan, Can, et al.
Publicado: (2023)

Recommendation of data-free class-incremental learning algorithms by simulating future data
por: Feillet, Eva, et al.
Publicado: (2024)

Multimodal synthesis of MRI and tabular data with diffusion in a joint latent space via cross-attention
por: Mensing, Daniel, et al.
Publicado: (2026)

Uni-Mlip: Unified Self-supervision for Medical Vision Language Pre-training
por: Bawazir, Ameera, et al.
Publicado: (2024)

Reducing self-supervised learning complexity improves weakly-supervised classification performance in computational pathology
por: Lenz, Tim, et al.
Publicado: (2024)

Generating floorplans for various building functionalities via latent diffusion model
por: Ibrahim, Mohamed R., et al.
Publicado: (2024)

Human alignment of neural network representations
por: Muttenthaler, Lukas, et al.
Publicado: (2022)

Semi-supervised Concept Bottleneck Models
por: Hu, Lijie, et al.
Publicado: (2024)

Permutation-equivariant quantum convolutional neural networks
por: Das, Sreetama, et al.
Publicado: (2024)

Feature Hallucination for Self-supervised Action Recognition
por: Wang, Lei, et al.
Publicado: (2025)

Self-supervised Learning for Hyperspectral Images of Trees
por: Rahman, Moqsadur, et al.
Publicado: (2025)

Self-supervised Transformation Learning for Equivariant Representations
por: Yu, Jaemyung, et al.
Publicado: (2025)

Defect detection using weakly supervised learning
por: Sevetlidis, Vasileios, et al.
Publicado: (2023)

Revisiting semi-supervised learning in the era of foundation models
por: Zhang, Ping, et al.
Publicado: (2025)

Detection of diabetic retinopathy using longitudinal self-supervised learning
por: Zeghlache, Rachid, et al.
Publicado: (2022)