Find Academic Supervisors

Massimo Poncino is a Full Professor at the Department of Control and Computer Science (DAUIN) within the Faculty of Engineering at Politecnico di Torino. He serves as Scientific Advisor for the STMicroelectronics partnership and coordinates basic engineering subjects. A Senior Member of IEEE since 2012 and Fellow since 2012, he has served on editorial boards for IEEE Transactions on Computer-Aided Design, IEEE Design & Test of Computers, and ACM Transactions on Design Automation. Education: Laurea in Electronic Engineering (1989) and PhD in Computer and Systems Engineering (1993) from Politecnico di Torino Academic Career: Visiting Scientist University of Colorado (1993-1994), Researcher at Politecnico di Torino (1995-2001), Associate Professor at University of Verona (2001-2004), Full Professor at Politecnico di Torino (2006-present) His research focuses on energy-efficient digital systems , including design automation of SoCs, hardware-aware AI, battery management, cyber-physical systems, and embedded systems. Recent publications highlight advancements in digital twins for batteries , low-power neural network deployment , and IoT privacy . Scientific Awards: Recognition of Service Award - ACM (2013) Certificate of Appreciation - IEEE Circuits and Systems Society (2006, 2008, 2009) IEEE Fellow (2012-) Research Involvement: EU H2020, VI/VII Framework Programs evaluator Scientific Director for projects: Approxim@ction, EMBAI, DISLO-MAN, DAMASCO Member of EDA research group Teaching: Course director for Energy Management for IoT (2019-2025) Lecturer for Computer Science courses (2003-2025)

• Digital Circuits and Systems
• Energy-Efficient Circuits and Systems
• Embedded Systems
• +7 more

Riccardo Cantoro is an Associate Professor in the Department of Control and Computer Science (DAUIN) at Politecnico di Torino, where he is a member of the College of Computer, Film and Mechatronics Engineering and the College of Mechanical, Aerospace and Automotive Engineering. He is affiliated with the CAD - Electronic CAD & Reliability Group and the CARS@PoliTO Interdepartmental Center for Automotive Research and Sustainable Mobility. His work bridges academic research and industrial applications through multiple commercially funded projects. Scientific Disciplinary Sector: IINF-05/A - Information Processing Systems ERC Sectors: PE7_4, PE6_2, PE6_11, PE6_12 His research focuses on functional safety, functional testing, and microprocessor testing, with a strong emphasis on embedded systems and reliability. He applies machine learning and formal methods to enhance test efficiency and system robustness, particularly in automotive and safety-critical domains. His work integrates computer-aided design, fault modeling, and resilience assessment in both hardware and AI systems. The recent publications highlight a trend toward data-efficient and intelligent testing methodologies, combining machine learning (e.g., TabPFN, active learning) with traditional electronic design automation. Topics include microcontroller performance screening, CNN resiliency, FeFET device testing, and system-level test optimization, reflecting a cohesive research agenda in trustworthy computing and hardware reliability. Scientific Awards: No awards explicitly mentioned in the provided texts. Advising and Grants: Dr. Cantoro supervises numerous PhD students in Computer and Systems Engineering, focusing on functional safety, test methodologies, and AI for CAD. He leads multiple industry-funded research projects, including collaborations with Infineon Technologies and Dana-TM4 Italia, on topics such as ATPG tools, speed monitor modeling, and power module reliability. His role as Scientific Manager/Head underscores his leadership in applied research and technology transfer. Labs and Teams: He is a core member of the CAD - Electronic CAD & Reliability Group (DAUIN) and contributes to the CARS@PoliTO center, fostering interdisciplinary research in automotive systems and sustainable mobility.

• Functional Safety
• Functional Testing
• Microprocessor Testing
• +9 more

Nicolò Bellarmino is a Researcher at the Department of Control and Computer Science (DAUIN), Politecnico di Torino, where he also serves as an External Lecturer and Teaching Assistant. His work is centered on machine learning applications in electronic design automation, particularly in microcontroller performance screening and reliability assessment of deep learning hardware. His research interests include machine learning for embedded systems, feature selection, neural network testing, and reliability engineering. He employs techniques such as evolutionary algorithms, transfer learning, and fault injection to develop efficient and robust methodologies for semiconductor testing and DNN accelerator validation. The recent publications highlight a strong focus on data-efficient and automated approaches for performance prediction and reliability assessment, leveraging foundation models, unsupervised learning, and hierarchical modeling. These works span journals and top-tier conferences in computer-aided design, electronics, and machine learning. He has no listed scientific awards in the provided text. Bellarmino actively contributes to teaching in the Computer Engineering and Aerospace Engineering programs, collaborating on courses such as Systems Programming, System and Device Programming, and Future of Work. He is a member of the CAD - Electronic CAD & Reliability Group (DAUIN), contributing to cutting-edge research in EDA and hardware reliability. No grants or advising roles are mentioned.

• Machine Learning
• Electronic Design Automation
• Reliability Engineering
• +7 more

Sophie Fosson is an Associate Professor in the Department of Control and Computer Science (DAUIN) at the Polytechnic University of Turin, Italy. She is a member of the System Identification & Control (SIC) research group and teaches courses such as Automatic Control and Modeling and Control of Cyberphysical Systems at both the master's and doctoral levels. Education: PhD in Mathematics for Industrial Technologies, Scuola Normale Superiore di Pisa Master’s in Mathematical Engineering, Politecnico di Torino Her research focuses on sparse optimization, machine learning, system identification, and control theory . She integrates mathematical modeling with practical applications in cyber-physical systems and neural networks. Her work emphasizes efficient and robust optimization techniques for deep learning and control systems. The recent publications highlight a strong trend in optimization of neural networks , particularly through sparse training, binary and ternary quantization, self-supervised learning, and fault tolerance . Her research bridges control theory with machine learning, applying mathematical rigor to modern AI challenges in safety-critical and embedded environments. Scientific Awards: No awards explicitly mentioned. She supervises several PhD students including Alice Re, Rosario Milazzo, and Simone Pirrera , and has been involved in research projects such as CRISP and collaborations with Centre Tecnològic de Telecomunicacions de Catalunya . She has held postdoctoral positions at DISMA and DET (Politecnico di Torino) and worked as a researcher at Istituto Superiore Mario Boella. Laboratories and Research Groups: System Identification & Control (SIC), DAUIN, Politecnico di Torin

• Sparse optimization
• Machine learning
• Convex and nonconvex optimization
• +7 more

Francesco Bellotti is an Associate Professor at the University of Genoa's Department of Naval, Electrical, Electronic and Telecommunications Engineering (DITEN). He teaches advanced courses including Computational Intelligence, Cyber Physical Systems, and Machine Learning for Automated Driving across master's programs in Electronic Engineering and Engineering Technology for Strategy and Security. His institutional role includes membership in the steering committee of the Italian Excellence Center for Logistics, Transport, and Infrastructure (CIELI). Bellotti's research focuses on artificial intelligence and embedded systems , with applications in automotive technology, edge computing, and TinyML. Key areas include real-time driver distraction detection, deep reinforcement learning for autonomous parking, neural architecture optimization for microcontrollers, and cross-domain activity recognition. His work bridges theoretical machine learning with resource-constrained hardware implementations. Recent publications (2024-2025) demonstrate a strong emphasis on optimizing deep learning models for edge deployment, particularly in automotive and IoT contexts. Dominant themes include real-time neural network inference on microcontrollers, adversarial training for robust autonomous agents, video preprocessing for driving scenarios, and benchmarking lightweight vision models. The research consistently targets efficiency-critical applications, reflecting Bellotti's focus on scalable embedded AI solutions.

• Artificial Intelligence
• Embedded Systems
• Automated Driving
• +3 more

Paolo Gastaldo serves as Associate Professor in the Department of Naval, Electrical, Electronic and Telecommunications Engineering (DITEN) at the University of Genoa's School of Engineering. His academic appointment focuses on electronic engineering (IINF-01/A classification) with teaching responsibilities spanning undergraduate and graduate programs including Electronic Engineering and Information Technologies. His research centers on machine learning for embedded systems, specializing in neural architecture search techniques optimized for resource-constrained environments. Key investigation areas include hardware-aware AI deployment on microcontrollers, energy-efficient traffic classification, and affordance segmentation for wearable robotics. His work bridges theoretical machine learning with practical hardware constraints, targeting applications in IoT security, edge computing, and smart wearable systems. Analysis of his recent publications reveals a strong trend toward Pareto-optimal solutions balancing computational efficiency and accuracy in neural network design. His research demonstrates particular expertise in adapting deep learning models for microcontroller deployment while maintaining cybersecurity functionality. The publications consistently address the challenge of implementing complex AI tasks within strict memory and power limitations of embedded devices. Gastaldo maintains active research supervision with regular publication output, primarily through the University of Genoa's institutional repository (IRIS). His work shows strong interdisciplinary connections between computer science, electrical engineering, and robotics applications.

• Machine Learning
• Embedded Systems
• Neural Architecture Search
• +4 more

Rodolfo Zunino serves as a Full Professor in the Department of Naval, Electrical, Electronic and Telecommunications Engineering (DITEN) at the University of Genoa. His teaching portfolio includes core electronics courses across multiple degree programs including Master's in Electronic Engineering and undergraduate programs in Electronics Engineering and Information Technology. His research focuses on the intersection of embedded systems and neural networks, with particular emphasis on hardware-aware optimization for resource-constrained environments. Key areas include traffic classification for cybersecurity, affordance segmentation for robotics, energy-efficient structural health monitoring, and in-sensor computing architectures. His work consistently addresses the Pareto optimization between computational efficiency and accuracy in embedded AI applications. Analysis of his recent publications (2023-2025) reveals a strong trend toward hardware-software co-design for neural networks, with increasing specialization in wearable robotics and structural monitoring systems. The research demonstrates consistent innovation in neural architecture search techniques specifically tailored for microcontrollers and sensor-embedded systems. Professor Zunino maintains active research supervision with multiple advisees (though specific names aren't listed in available materials) and collaborates on projects involving hardware implementation of neural networks for security and monitoring applications. His work receives consistent publication in relevant engineering venues. His laboratory activities center around embedded electronic systems development, with focus areas in neural network acceleration for microcontrollers, sensor data processing, and real-time system implementation for robotics and infrastructure monitoring applications.

• Embedded Systems
• Neural Networks
• Hardware-Aware Neural Architecture Search
• +7 more

Nicolo' Bellarmino is a Research Fellow and Research Assistant at the Department of Automatic Control and Computer Science (DAUIN) of Politecnico di Torino. His roles include teaching and collaborating in courses such as System Programming, Computer Science, and Future of Work across Computer Engineering and Aerospace Engineering programs. He is affiliated with the CAD - Electronic CAD & Reliability Group (DAUIN), focusing on research in machine learning, embedded systems, and hardware testing. His research interests center on computational intelligence applied to computer-aided design, particularly in machine learning techniques for microcontroller performance screening. He has also explored neural network resiliency, fault detection in CNNs, and device-aware testing methodologies. Recent work emphasizes compressed sensing, feature selection, and transfer learning in resource-constrained systems. Bellarmino's publications span conference proceedings and journals, addressing challenges in embedded systems testing, neural network optimization, and biomedical applications like COVID-19 detection via exhaled breath analysis. His contributions bridge theoretical machine learning advancements with practical hardware validation and optimization. He actively contributes to academic teaching, maintaining an email contact at nicolo.bellarmino@polito.it for professional inquiries.

• Machine Learning
• Computer-Aided Design (CAD)
• Embedded Systems
• +3 more

Prof. Paolo Crippa is an Associate Professor at the Department of Information Engineering (DII) of the University of Ancona (Università Politecnica delle Marche), Italy. His research focuses on biomedical signal processing, embedded systems, and wearable technology for healthcare applications. He specializes in neural networks, sensor design, and nanoelectronics, with notable contributions to graphene-based biosensors and real-time gesture recognition systems. His work bridges electronics, machine learning, and healthcare, addressing challenges in disease diagnosis, activity monitoring, and assistive living technologies. Prof. Crippa’s publications emphasize the development of low-power, high-accuracy systems for applications such as EEG-based disease classification, wearable sensors for activity recognition, and SARS-CoV-2 detection using advanced materials. His recent work includes optimizing LSTM neural networks for embedded platforms and integrating multimodal sensors (PPG, IMU, sEMG) for health monitoring. His research trends reveal a strong emphasis on applying machine learning to biomedical signals, improving sensor synchronization, and leveraging nanotechnology for diagnostic tools. He also explores open-source hardware/software co-design frameworks for system-on-chip (SoC) development. Prof. Crippa’s contributions extend to international collaborations and interdisciplinary projects, reflecting his role in advancing both theoretical and applied aspects of information engineering.

• Biomedical Signal Processing
• Embedded Systems
• Neural Networks
• +5 more

Prof. Laura Falaschetti is a Researcher at the Department of Information Engineering, Polytechnic University of Marche (Ancona, Italy). Her work focuses on embedded systems, neural networks, biomedical engineering, and signal processing. She develops lightweight machine learning models for resource-constrained devices, with applications in healthcare monitoring, environmental sensing, and wearable technology. Key projects include real-time gesture recognition systems, EEG-based disease classification, and low-power IoT devices for disaster early warning. Her research integrates hardware-software co-design (e.g., QEMU/GHDL) and emphasizes practical deployment of AI algorithms on microcontrollers. She holds office hours every Friday 10:00-13:00 at Ufficio docente Q165 DII/Microsoft Teams. Contact: l.falaschetti@staff.univpm.it Publications highlight contributions to embedded vision systems, wearable sensor networks, and multimodal signal fusion for clinical applications. Her work bridges theoretical machine learning with practical embedded system constraints, addressing challenges in energy efficiency, real-time processing, and medical accuracy.

• Embedded Systems
• Neural Networks
• Biomedical Engineering
• +3 more

Silvia Liberata Ullo is a Researcher at the Department of Engineering (DING) of Università del Sannio . Her work spans Remote Sensing , Machine Learning , and Telecommunications , with a focus on Environmental Monitoring and Public Health Applications . Key research areas: Deep Learning for Land Cover Mapping Speckle Noise Reduction in SAR Data Machine Learning for Pandemic Response Mixed Reality in Military Systems Her recent publications highlight advancements in 2025 : Deep Learning for Land Cover Classification using Sentinel-1 2024 : Ensemble ML models for Dengue Outbreak Forecasting in Brazil/Peru 2023 : SAR Image Enhancement via Residual Neural Networks She collaborates with international institutions on climate-health services and geospatial AI projects.

• Remote Sensing
• Machine Learning
• Deep Learning
• +5 more

Riccardo Berta is an Associate Professor at the Department of Naval, Electrical, Electronic, and Telecommunications Engineering (DITEN), University of Genoa. His research focuses on TinyML, deep learning on microcontrollers, and embedded systems for automotive and IoT applications. Current Affiliation: Department of Naval, Electrical, Electronic, and Telecommunications Engineering (DITEN), University of Genoa Academic Role: Associate Professor, Electronics (IINF-01/A) His research interests include: Tiny Machine Learning (TinyML) for resource-constrained devices Deep Reinforcement Learning in automated driving and gaming Edge Computing and Structural Health Monitoring IoT frameworks for data management and serious games Recent work explores the application of neural networks, adversarial training, and synthetic dataset generation in automotive scenarios. He is a member of the Scientific Council of the University Service Center for Simulation and Advanced Training (SIMAV) and the Department Board of DITEN.

• Tiny Machine Learning
• Reinforcement Learning
• Deep Learning on Microcontrollers
• +5 more

Alessio Burrello is a Researcher at the Department of Control and Computer Engineering (DAUIN) , affiliated with Politecnico di Torino . His academic career is oriented toward Machine Learning , Deep Learning , and Embedded Systems . Research Interests : Burrello focuses on AI compilers , neural network optimization for edge devices, distributed systems , and signal processing applications . His work spans interdisciplinary domains like energy management for IoT , neuromorphic computing , and biomedical monitoring . Recent Publications highlight his contributions to TinyML , low-power microcontrollers , and heterogeneous computing . Notable works include optimizing DNN inference on multi-accelerator SoCs and deploying compact transformers for seizure detection. Teaching : Burrello has been a course owner for 'Optimized Execution of Neural Networks at the Edge' in the Computer and Systems Engineering program since 2024/25. He also contributes to courses in Agritech Engineering and Aerospace Engineering . Supervision : He supervises Javier Jesus Poveda Rodrigo , a PhD candidate in Artificial Intelligence , and participates in commercial research projects like Efficient Active Inference Deployment .

• Machine Learning
• Deep Learning
• AI Compilers
• +7 more