Deep Learning (DL) has achieved remarkable success in tackling complex Artificial
Intelligence tasks. The standard training of neural networks employs backpropagation to …

In the past few decades, there have been multiple algorithms proposed for the purpose of
solving optimization problems including Machine Learning (ML) applications. Among these …

Offline signature verification necessitates the involvement of machine learning visual
recognition techniques. Efficient signature e-verifiers in machine learning and data analysis …

Riemannian meta-optimization provides a promising approach to solving non-linear
constrained optimization problems, which trains neural networks as optimizers to perform …

Laplacian Eigenmaps (LE) is a widely used dimensionality reduction and data
reconstruction method. When the data has multiple connected components, the LE method …

Identification of lymph node metastases with histopathology images is crucial for cancer
diagnosis. Deep learning-based approaches have been applied to detect cancer …

Metric learning focuses on finding similarities between data and aims to enlarge the
distance between the samples with different labels. This work proposes a semi-supervised …

Traditional partial least squares regression typically takes vectorized data into account. The
process of vectorizing images may disrupt the inherent structural information of the data …

This chapter presents a composition of personal observations experienced in industrial
research lab settings over many years. It is not structured in a conventional paper style …

ABSTRACT Traditional Partial Least Squares Regression (PLSR) models frequently
underperform when handling data characterized by uneven categories. To address the …