Academic Editor: Garzia Fabio Received: 20 February 2025 Revised: 28 March 2025 Accepted: 1 April 2025 Published: 8 April 2025 Citation: Boulealam, C.; Filali, H.; Riffi, J.; Mahraz, A.M.; Tairi, H. Deep Multi-Component Neural Network Architecture. Computation 2025, 13, 93. https://doi.org/10.3390/ computation13040093 Copyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/ licenses/by/4.0/). Article Deep Multi-Component Neural Network Architecture Chafik Boulealam 1, * , Hajar Filali 1,2 , Jamal Riffi 1 , Adnane Mohamed Mahraz 1 and Hamid Tairi 1 1 LISAC, Department of Computer Science, Faculty of Science Dhar El Mahraz, Sidi Mohamed Ben Abdellah University, Fez 30000, Morocco 2 Laboratory of Innovation in Management and Engineering (LIMIE), I ´ SGA, Fez 30000, Morocco * Correspondence: chafik.boulealam@usmba.ac.ma Abstract: Existing neural network architectures often struggle with two critical limita- tions: (1) information loss during dataset length standardization, where variable-length samples are forced into fixed dimensions, and (2) inefficient feature selection in single- modal systems, which treats all features equally regardless of relevance. To address these issues, this paper introduces the Deep Multi-Components Neural Network (DMCNN), a novel architecture that processes variable-length data by regrouping samples into compo- nents of similar lengths, thereby preserving information that traditional methods discard. DMCNN dynamically prioritizes task-relevant features through a component-weighting mechanism, which calculates the importance of each component via loss functions and adjusts weights using a SoftMax function. This approach eliminates the need for dataset standardization while enhancing meaningful features and suppressing irrelevant ones. Ad- ditionally, DMCNN seamlessly integrates multimodal data (e.g., text, speech, and signals) as separate components, leveraging complementary information to improve accuracy with- out requiring dimension alignment. Evaluated on the Multimodal EmotionLines Dataset (MELD) and CIFAR-10, DMCNN achieves state-of-the-art accuracy of 99.22% on MELD and 97.78% on CIFAR-10, outperforming existing methods like MNN and McDFR. The architecture’s efficiency is further demonstrated by its reduced trainable parameters and robust handling of multimodal and variable-length inputs, making it a versatile solution for classification tasks. Keywords: deep learning (DL); image classification; meaningful neural network (MNN); multimodal; deep multi-components neural network architecture (DMCNN); neural network architecture 1. Introduction 1.1. Research Background Deep learning has revolutionized the field of artificial intelligence by providing a natural way to extract meaningful feature representations from raw data without relying on hand-crafted descriptors. Feature extraction plays a critical role in various applications, as it reduces input dimensionality [1] while enabling a more meaningful representation that uncovers underlying patterns and relationships. Representation learning, a cornerstone of deep learning, significantly enhances the ability to extract useful information when building classifiers or other predictors [2]. A good representation not only captures the posterior distribution of the underlying data but also serves as a foundation for achieving superior predictive results. Over the years, numerous architectures have been proposed to address challenges such as overfitting, information loss during dataset preprocessing, and the need to extract the most informative features while ignoring irrelevant ones. Computation 2025, 13, 93 https://doi.org/10.3390/computation13040093