Artificial Intelligence (AI) has a rich history dating back to the early 1950s, but in recent times, the spotlight has been on Deep Learning (DL), a disruptive technology driving numerous breakthroughs in the neuro computing (NC) ecosystem. DL's remarkable ability to analyze images, videos, and unstructured data has surpassed traditional Machine Learning (ML) techniques, ushering in new possibilities. The growth of NC has been remarkable, evolving from the three-layered Neural Network (NN) to the more powerful multi-layered DL, and subsequently advancing into Transfer Learning (TL), Federated Learning (FL), and the cutting-edge Split Learning (SL). The rapid pace of progress suggests that a new "X Learning" technique may emerge each decade, building on the achievements of its predecessors with innovative designs and enhancements. Each milestone brings unique technical contributions, accompanied by its own advantages and challenges, spanning security, complexity, deployment, and potential application domains. This talk will delve deeply into these diverse milestones, exploring their underlying technologies, applications, and the associated challenges they present. Particular focus will be given to FedFaSt, a novel ML technique that leverages the "Fittest Aggregation" and "Slotted Training" paradigm to significantly improve the performance of Federated Learning. FedFaSt represents a promising advancement in the field, effectively addressing some of the limitations of conventional FL and pushing the boundaries of decentralized machine learning. By providing a comprehensive overview of the historical progress and contemporary advancements in AI, this talk seeks to offer valuable insights into the constantly evolving landscape of Deep Learning and its related techniques, igniting inspiration for further research and innovation in the field of Artificial Intelligence.
Bigomokero Antoine Bagula holds a Ph.D. degree (Tech. Dr.) in Communication Systems from the Royal Institute of Technology (KTH) in Stockholm, Sweden. Additionally, he earned two MSc degrees, one in Computer Engineering from the Université Catholique de Louvain (UCL) in Belgium and another in Computer Science from the University of Stellenbosch (SUN) in South Africa.Currently, Dr. Bagula serves as a full professor in the Department of Computer Science at the University of the Western Cape (UWC) in South Africa where he also leads the Intelligent Systems and Advanced Telecommunication (ISAT) laboratory. Furthermore, he holds a professorial position at ESIS-Salama in the Democratic Republic of the Congo (DRC), where he is in charge of spearheading the institution's research and innovation agenda through the "Centre de Recherche et Développement en Informatique Appliquée (CREDIA)" research center. Dr. Bagula's current research interests span a wide range of topics, including Data Engineering with a focus on Big Data Technologies, Cloud/Fog Computing, and Network Softwarization, encompassing concepts such as NFV and SDN. He is actively engaged in exploring the potential of the Internet of Things (IoT), which includes both the Internet-of-Things and Tactile Internet-of-Things. Additionally, he is deeply invested in Data Science, with a particular emphasis on Artificial Intelligence, Machine Learning, and their applications in the realm of Big Data Analytics. Dr. Bagula's expertise extends to Next Generation Networks (NGN), including the realms of 5G/6G. Through his academic achievements and research endeavors, Prof. Bagula continues to make a significant impact on the fields of computer science, data engineering, and telecommunications.