Associate Professor and Department Chair, at the Department of Electrical and Computer Engineering, at the University of Cyprus
Prof. Theocharis (Theo) Theocharides is an Associate Professor and the Department Chair, at the Department of Electrical and Computer Engineering, at the University of Cyprus and the Director of Research of the KIOS Research and Innovation Centre of Excellence. He is a senior member of the IEEE and the IEEE Computer Society, a member of the ACM, and a member of the HiPEAC Network of Excellence. He is an Associate Editor for ACM’s Computing Surveys, ACM’s Transactions on Emerging Technologies for Computing Systems (JETC), IEEE Transactions on Computer Aided Design of Integrated Circuits and Systems (TCAD) and the IEEE Design and Test magazine. He also serves on several Organizational and Technical Program Committee boards of various IEEE/ACM Conferences, most recently being the Technical Programme Committee Chair of the 2025 edition of the Design, Automation and Test in Europe (DATE), the largest conference in Electronic Design and Automation of Integrated Circuits and Embedded Systems. His present work focuses on development of embedded machine learning algorithms (tinyML) and applications, embedded computer vision, and edge AI algorithms for autonomous unmanned aerial and terrestrial vehicles.
Keynote Speech
Dynamic Early-Exit Convolutional Neural Networks for Edge Vision: Do only what and when you need!
While computer vision has seen unparalleled growth over recent years, mainly due to advancements in deep convolutional neural networks, deploying such models on edge devices such as tiny autonomous unmanned aerial and terrestrial vehicles has been challenging, due to constraints involving power and energy, computational resources and memory footprint, and application performance requirements. Applications in safety-critical missions such as search and rescue operations and emergency management, elevate these challenges, as they also impose performance constraints, in addition to visual constrains associated with the inference due to occlusions, changing environmental parameters, and dynamic operational and situational context. Current practice involves performing training of the CNNs in a way that generalizes to all these constraints and optimizing the model to target an embedded processing device, custom accelerator or an embedded multi-processor platform. While methods such as pruning (structured and unstructured) and quantization have achieved various levels of success in compressing and optimizing deep CNNs for embedded devices, they remain subject to the computational boundaries imposed by the host platforms.
Leveraging from the benefits of adaptive inference in dynamic deep CNNs, in this talk I will present our recent work in dynamic deep convolutional neural networks targeting low power embedded computer vision applications. In particular, Dynamic Deep Convolutional Neural Networks (DNNs) offer significant resource savings over static CNNs in edge computer vision by adapting their computation based on input complexity. Unlike static models that process every input with a fixed depth and width, dynamic DNNs selectively activate layers, channels, or early exits, reducing unnecessary computation and memory access. This conditional execution leads to lower energy consumption, faster inference, and improved efficiency—making dynamic architectures ideal for real-time, resource-constrained edge applications.
Professor and SenSIP Center Director in the School of Electrical, Computer, and Energy Engineering at Arizona State University (ASU)
Andreas Spanias is Professor in the School of Electrical, Computer, and Energy Engineering at Arizona State University (ASU). He is also the director of the Sensor Signal and Information Processing (SenSIP) center and the founder of the SenSIP industry consortium (also an NSF I/UCRC site). His research interests are in the areas of adaptive signal processing, speech processing, quantum machine learning and sensor systems. He and his student team developed the computer simulation software Java-DSP and its award-winning iPhone/iPad and Android versions. He is author of two textbooks: Audio Processing and Coding by Wiley and DSP; An Interactive Approach (2nd Ed.). He contributed to more than 350 papers, 11 monographs, 21 full US patents, 10 provisional patents and several IP pre-disclosures. He served as Associate Editor of the IEEE Transactions on Signal Processing and as General Co-chair of IEEE ICASSP-99. He also served as the IEEE Signal Processing Vice-President for Conferences. Andreas Spanias is co-recipient of the 2002 IEEE Donald G. Fink paper prize award and was elected Fellow of the IEEE in 2003. He served as Distinguished Lecturer for the IEEE Signal processing society in 2004. He is a series editor for the Morgan and Claypool lecture series (now under Springer) on algorithms and software. He co-authored with his students a paper on Quantum Fourier transforms for signal analysis-synthesis at ICASSP 2023 that received a Top 3% rating certificate. He was also co-author on an SPIE 2023 publication on deep learning that won a Best Paper award. He is currently heading four NSF workforce development projects as a PI. He received the 2018 IEEE Phoenix Chapter award with citation: “For significant innovations and patents in signal processing for sensor systems.” He also received the 2018 IEEE Region 6 Outstanding Educator Award (across 12 states) with citation: “For outstanding research and education contributions in signal processing.” He was elected recently to Senior Member of the National Academy of Inventors (NAI). Andreas Spanias was named Fulbright U.S. Research Scholar and will conduct research in machine learning for energy and other applications at UKIM in Skopje.
Keynote Speech
A Fulbright US Scholar Project on Research and Workforce Development in AI for Solar Energy Applications
This CWSPI presentation highlights a Fulbright-supported research and workforce development initiative on classical and quantum machine learning (QML) for solar energy applications. Originating at Arizona State University’s SenSIP Center, the program launched ML projects in solar energy, imaging, and audio signal processing, while hosting five NSF-sponsored efforts to train students and faculty. In 2024, workforce development and research in energy systems expanded internationally through a Fulbright U.S. Scholar grant, fostering collaboration with universities in the Balkans. The program combined research, student training, and outreach through seminars at regional universities. Recent efforts also introduced QML simulations and tutorials aimed at building local capacity. This seminar presents insights and outcomes from the Fulbright experience, emphasizing the role of ML and QML in advancing solar energy solutions and supporting workforce development through international research engagement.