Advances in Machine and Deep Learning

Dear Colleagues,

Recent years have witnessed remarkable advancements in machine learning (ML) and deep learning (DL), propelling breakthroughs across diverse scientific domains. These technologies have revolutionized medical diagnostics and significantly automated industrial processes, showcasing their profound impact. The Special Issue titled “Advances in Machine and Deep Learning” aims to capture the latest breakthroughs, innovative applications, and theoretical progress shaping these dynamic fields’ future.

ML involves developing and analyzing algorithms that enable computers to autonomously learn from data, deriving rules to predict outcomes for new data. Traditionally, this process encompasses problem definition, data collection, model development, and result validation. However, the rapid evolution of artificial intelligence (AI) has broadened the scope of ML applications, necessitating novel approaches.

DL, powered by advanced feature engineering techniques, surpasses traditional ML limitations, achieving superior performance and facilitating complex applications. While DL has established itself in supervised learning, research in unsupervised and reinforcement learning continues to evolve. It excels in speech and image recognition tasks, leveraging models like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).

Despite its strengths, DL presents challenges. It requires extensive and diverse datasets and meticulous parameter tuning. Excessive model training can cause overfitting, limiting applicability across different domains. Moreover, the opacity of DL models complicates understanding their learning and decision-making processes, posing significant challenges for researchers.

Explainable AI (XAI) techniques aim to address these challenges by making DL models more interpretable and transparent. These methods enhance trust in AI systems and provide insights into how decisions are made, which is critical for fields where transparency is crucial, such as healthcare, finance, agriculture, and so on. XAI provides both ante-hoc models, mainly ML algorithms, and post hoc models, which are useful, for example, in completely black-box models such as DL neural networks.

Furthermore, this issue will delve into advances in Natural Language Processing (NLP) and Large Language Models (LLMs), another critical area of AI research. NLP focuses on enabling computers to comprehend, interpret, and generate human language, presenting unique challenges and opportunities within AI. LLMs represent a significant leap in NLP capabilities, leveraging vast amounts of text data to produce contextually relevant responses and handle complex language tasks. This advancement holds the potential to transform how we communicate and process information. The development of LLMs has also stimulated research into more efficient training methods, ethical considerations such as bias reduction, and their application across diverse sectors, including healthcare, finance, and education.

This Special Issue aims to foster the development of ML and DL methodologies, promote their practical implementation, and address ongoing challenges in various fields. This will open new avenues for applications and innovations in AI and beyond.

Contributions to this issue will explore:

• Simplifying parameter complexity in DL models.
• Develop transparent methods to clarify hidden components and validate model outputs.
• Introducing adaptive evolution and model refinement through weight adjustments and structural pruning.
• Exploring innovative ML and DL techniques and integrating them with established architectures.
• Advancing soft computing and AI environments using DL, expanding applications across big data, IoT, social media mining, and web applications.
• Advancements in NLP algorithms for text classification, sentiment analysis, and machine translation.
• Integrating DL techniques with NLP for enhanced language understanding and generation.
• Ethical considerations in NLP, including bias mitigation and fairness in language processing models.
• Applications of NLP in healthcare, finance, customer service, and other domains.
• Innovations in multilingual NLP models and cross-lingual transfer learning.
• Applications and issues regarding LLM.

Dr. Cristian Randieri
Dr. Riccardo Pecori
Dr. Giuseppe Tradigo
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Machine Learning and Knowledge Extraction is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• machine learning (ML)
• deep learning (DL)
• artificial intelligence (AI)
• supervised learning
• unsupervised learning
• reinforcement learning
• convolutional neural networks (CNNs)
• recurrent neural networks (RNNs)
• natural language processing (NLP)
• large language models (LLMs)
• parameter tuning
• overfitting
• transparent models
• ethical AI
• bias mitigation
• explainable AI (XAI) techniques
• pervasive ML e DL