Professor  Said Sanei

 Imperial College London and NTU

Professor  Abdolreza Abhari

Toronto Metropoulian University

 Title

Migration from Signal Processing to Generative AI

Summary: With increasing the data volume and the diversity of techniques for realistic data generation there is a strong motivation for using AI, particularly with the help of deep learning, as compared to developing and implementation of signal processing or the traditional machine learning systems. In this talk the anatomy of this migration will be discussed and several examples in assessing large biomedical data, surrogate data generation, and applications to bioengineering and brain studies will be presented. We will also see how the uncertainty in data labelling can be incorporated in the signal processing formulation to improve the clinical diagnosis. Recent works on deep learning reflect strong enthusiasm for generative AI where the human interactions with the learning system can significantly improve the AI performance.

Title

Evolution of simulation with data science and artificial intelligence

Summary: Computer simulation of engineering systems is one of the popular methods for evaluating systems that are impossible or very expensive to test after implementation. In recent years, the use of artificial intelligence has caused many changes, especially in the construction of smart cities and smart connections, such as the Internet of Things (IoT) and 5G networks, and video analysis and information and text processing in social networks.  Finally, the modeling of the parameters needed to simulate these systems needs to be studied and reconstructed again. This discussion first examines the new advancements of simulators through the use of artificial intelligence and the possibilities that digital twin provides for industries, and then studies some examples of using artificial intelligence methods in modeling video analysis and building social networks simulators.