AI-Driven Development of High-Performance Electronic Systems and Applications
Rationale:
The integration of Artificial Intelligence (AI) into the design of high-performance electronic systems represents a transformative shift in computer architecture and circuit design. As modern electronic systems grow increasingly complex, AI-driven methodologies offer unprecedented advantages in optimization, automation, and performance enhancement. Beyond system design, AI is also playing a crucial role in the development of intelligent applications that run on embedded and high-performance electronic systems.
This special session aims to explore the latest advancements and emerging trends in AI for both the design and development of high-performance electronic systems, including but not limited to circuit synthesis, system-level optimization, and verification, as well as AI-powered applications that leverage these systems for demanding computing tasks in resource-constrained environments.
The relevance of this topic stems from the increasing demand for high-performance, energy-efficient, and scalable hardware architectures and applications in domains such as cloud computing, edge devices, and AI accelerators. Traditional design methodologies struggle to keep pace with these demands due to the sheer scale and intricacy of modern systems. AI-powered design tools and applications leveraging machine learning models, reinforcement learning techniques, and generative design approaches provide innovative solutions by enabling automated design space exploration, improving performance-per-watt metrics, and accelerating time-to-market.
Moreover, this topic is inherently multidisciplinary, bridging expertise from AI, hardware design, software engineering, electronic design automation (EDA), and optimization techniques. It invites researchers and practitioners from diverse backgrounds, including academia and industry, to discuss the synergies between AI and electronic system co-design. This session will foster collaborations between AI researchers, hardware engineers, and software developers, leading to novel methodologies that redefine how electronic systems are conceived, optimized, and applied to real-world challenges.
Topics of interest for this special session include, but are not limited to:
- AI-driven design space exploration for high-performance circuits and architectures.
- Machine learning techniques for power, performance, and area optimization.
- Reinforcement learning applications in electronic design automation (EDA).
- AI-assisted hardware verification, testing, and fault prediction.
- Generative AI for automated circuit synthesis and layout optimization.
- Integration of AI in FPGA and ASIC design workflows.
- Case studies of AI-enabled design methodologies in real-world applications.
- AI-powered applications in embedded systems.
- Optimization of AI workloads for edge computing and IoT devices
- Case studies of AI-enabled design methodologies and application development in real-world scenarios.
By bringing together experts in AI and electronic design, this session will provide a valuable platform for discussing cutting-edge research and practical applications, ultimately advancing the state of the art in high-performance electronic systems. We believe that this topic aligns and complements perfectly with the themes of DCIS and will attract significant interest from the research community and industry professionals alike.
Short-bio of the organizers
Soledad Escolar holds a Ph.D. in computer science and technology from the University Carlos III de Madrid in 2010 with honors. In September 2015, she joined the University of Castilla La Mancha (UCLM) as a post doctoral researcher and in 2020 she took possession of the position of associate professor at the same university. Since 2021, she has been appointed as the deputy director of the Academic Planning and Smart ESI at the School of Computer Science. Her research career has focused mainly on the study of a wide range of problems related to distributed systems, more specifically, sensor networks and their evolution towards the Internet of Things, specifically application portability in heterogeneous environments, communication protocols, synchronization, mobility, models, and energy efficiency management algorithms in energy harvesting devices.
Jesús Barba Romero holds a Bachelor’s degree in Computer Science (2001) and a PhD in Computer Engineering from the University of Castilla-La Mancha (2008). He works as an Associate Professor at the School of Computer Science (University of Castilla-La Mancha), and is a member of he ARCO group where he develops his research career since 2000. Currently, his research focuses on the development of computer vision and artificial intelligence solutions for heterogeneous devices, with a particular interest in SoC-FPGA architectures. He has served as Principal Investigator on several Spanish research projects and knowledge transfer contracts to the industry. From 2012 to 2015, he was a member of the management team of the School of Computer Science in Ciudad Real, serving as Academic Deputy Director again during the second half of 2022. He is also a founding partner of Inwire S.L., a UCLM spin-off established in January 2022. This technology-based company specializes in the development of custom solutions, leveraging the knowledge and expertise of the ARCO research group.
Neuromorphic Circuits, Systems, and Technologies
Rationale:
The field of neuromorphic engineering—inspired by the structure, dynamics, and functionality of the biological brain—has emerged as a frontier in electronic design, offering transformative potential across domains such as artificial intelligence, sensory processing, robotics, and edge computing. This special session aims to highlight the growing relevance, multidisciplinary nature, and unique design challenges and opportunities of neuromorphic circuits and systems within the context of modern electronic design.
Neuromorphic technologies push beyond conventional von Neumann architectures by leveraging event-driven, massively parallel, and energy-efficient hardware. These architectures are not only crucial for advancing brain-inspired computation but are also pivotal in developing next-generation low-power intelligent devices capable of real-time learning, adaptation, and decision-making.
The session will bring together contributions that span multiple disciplines, including:
- Analog and mixed-signal circuit design for implementing neuron and synapse models,
- Emerging memory technologies (e.g., memristors, phase-change memory) that support synaptic plasticity,
- Digital neuromorphic processors and system architectures for scalable, efficient deployment,
- Computational neuroscience and algorithmic frameworks that inform hardware design,
- Applications in edge AI, autonomous systems, biomedical interfaces, and real-time sensing.
The cross-disciplinary nature of neuromorphic systems fosters collaboration between electrical engineering, computer science, neuroscience, and materials science, making this topic especially timely and valuable for the electronic design community.
Organizers:
Koldo Basterretxea is currently an Associate Professor at the Department of Electronics Technology, University of the Basque Country (UPV/EHU). He is the Director of the Master in Advanced Electronic Systems and member of the Advisory Committee of the SoC4sensing Business-University Chair, both at the UPV/EHU. His research interest include the design of domain-specific digital processors for edge AI/ML, the real-time processing of hyperspectral imaging with application to autonomous navigation, and the use of neuromorphic event-based vision sensors (DVS) in the development of intelligent vision systems.
Antonio Rubio is currently an Emeritus Professor at the Universitat Politècnica de Catalunya (UPC), where he serves as the Director of the UPC Chip Chair in Advanced Architectures and Photonic Circuits, and a Visiting Professor at the Barcelona Supercomputing Center (BSC). His research interests focus on the topics of the chair, as well as emerging and unconventional computing technologies.
Teresa Serrano-Gotarredona (Senior Member, IEEE) is currently a CSIC Full Research Professor and Director of the Institute of Microelectronics of Sevilla (IMSE-CSIC-US). Since January 2006, she is also part-time professor at the Department of Computer Architecture and Technology of the University of Seville. Her research interests include analog circuit design of linear and nonlinear circuits, VLSI neural based pattern recognition systems, VLSI implementations of neural computing and sensory systems, transistor parameter mismatch characterization, learning systems with nanoscale memristor-type devices, and real-time vision sensing and processing chips. She has done important contributions in the field of low power low current analog circuits and also in architecture design of bioinspired vision sensors, and neural computing and learning bioinspired systems.
