In this Special Issue we gathered ten exemplary papers, each delineating advancements within the spheres of machine learning and deep neural networks. Commencing with a thorough exploration by Figueira and Vaz, readers are introduced to the nuances of synthetic data generation and evaluation, followed closely by Silva and Pedroso's systematic approach to leveraging deep reinforcement learning within the intricate realm of delivery logistics. Kamran et al. contribute an astute methodology for camouflage object segmentation, whereas Pinheiro and collaborators offer a crafted semi-supervised strategy for predicting EGFR mutations via CT images. Subsequent contributions, such as Lee and Yoo's framework for portrait emotion recognition and Balakrishnan et al.'s analytical exploration of transformer models for Twitter disaster detection, further exemplify the depth of research contained herein. Later chapters cover a broad spectrum of themes: Li, Branco, and Zhang investigate house price prediction; Aziz and his team delve into the geo-spatial analysis of hate speech; Nazari, Branco, and Jourdan introduce innovations in GAN training methodologies; and Xie and Lin present CNN models meticulously tailored for ectopic beat classification. In its entirety, this Special Issue represents progressive strides in machine learning and deep neural networks made by distinguished scholars. It offers readers an insightful overview of both the current state-of-the-art methodologies and the burgeoning innovations within this exciting field.