Diseases and nutritional deficiencies have the potential to seriously impact the production
yield and proper development of perennial species such as grapevine. The distinction …

As an emerging and popular technique for boosting CNNs, structural reparameterization
(SR) decouples the training and inference structures to alter the training dynamics and …

Interpreting complex deep networks, notably pre-trained vision-language models (VLMs), is
a formidable challenge. Current Class Activation Map (CAM) methods highlight regions …

We propose an empirical approach centered on the spectral dynamics of weights--the
behavior of singular values and vectors during optimization--to unify and clarify several …

HyperNetX (HNX) is an open source Python library for the analysis and visualization of
complex network data modeled as hypergraphs. Initially released in 2019, HNX facilitates …

With the popularity of edge computing devices and increasing complexity of convolutional
neural network (CNN) models, the need for model compression and acceleration has …

Within the framework of deep learning we demonstrate the emergence of the singular value
decomposition (SVD) of the weight matrix as a tool for interpretation of neural networks (NN) …

Deep learning has demonstrated remarkable advancements in the field of infrared point
objects classification. However, the challenge lies in explaining the reasons behind their …

This thesis explores the application of artificial intelligence, specifically using autoencoder
(AE) and variational autoencoder (VAE), for anomaly detection, when dealing with data …

A new robust variant of the formulation of the problem and the method of searching for the
principal components is considered. It is based on the application of differentiable estimates …