Zilverling

A. Yousefzadeh PhD (Amir)

Universitair docent
EEMCS-CS-CAES
Zilverling 5039
a.yousefzadeh@utwente.nl
+31534897988
Visitekaartje

Ik ben in februari 2024 bij de Universiteit Twente begonnen als universitair docent edge AI. Mijn focus ligt op het ontwerpen van embedded AI en neuromorfische systemen.


Kort CV:


Ph.D. in neuromorfische engineering bij IMSE, proefschrift: Digital Design For Neuromorphic Bio-Inspired Vision Processing

2018-2020: Bij de startup GrAI Matter Labs, later overgenomen door SNAP, heb ik voornamelijk gewerkt aan de architectuur van de NeuronFlow-processor

2020-2024: Bij imec, bij de Hardware Efficient AI-groep, heb ik voornamelijk gewerkt aan de architectuur van de SENECA-processor

2024-heden: universitair docent, Computer Architecture for Embedded Systems

Expertises

  • Computer Science

    • Computer Hardware
    • Neural Network
    • Artificial Intelligence
    • Energy Efficient
    • Electronic Learning
    • Edge AI
    • Multicore

  • Engineering

    • Internet-Of-Things

Organisaties

Onderzoekservaringen:

  • Neuromorfische detectie en verwerking
  • Ingebedde AI

Ik gebruik uitgebreid digitale hardware-ontwerptools en gate-level simulaties om hardware-architecturen te co-optimaliseren met neurale netwerkalgoritmen. Enkele van mijn technische ervaringen:

  • Ontwerp van programmeerbare neuromorfische processoren voor ingebedde AI-toepassingen
  • On-device leeralgoritmen en hardwareversnellers
  • Bio-geïnspireerde visuele verwerking
  • Benchmarking en vergelijking van verschillende algoritme-optimalisaties in hardware

Op zoek naar PhD- of postdoc-posities: kijk op de UTwente-carrièrewebsite. Alle posities worden daar geadverteerd en sollicitaties moeten online worden ingediend. Stuur uw sollicitatie niet per e-mail.

Op zoek naar masterscriptie of stage: stuur me een e-mail met uw cv en cijfers (zowel bachelor als master).

Publicaties

2025

Efficient Synaptic Delay Implementation in Digital Event-Driven AI Accelerators (2025)[Working paper › Preprint]. ArXiv.org. Meijer, R., Detterer, P., Yousefzadeh, A., Patino-Saucedo, A., Tang, G., Vadivel, K., Xu, Y., Gomony, M.-D., Corradi, F., Linares-Barranco, B. & Sifalakis, M.https://doi.org/10.48550/arXiv.2501.13610

2024

EON-1: A Brain-Inspired Processor for Near-Sensor Extreme Edge Online Feature Extraction (2024)IEEE Transactions on Circuits and Systems for Artificial Intelligence, 1(2), 128-140. Article 10744412. Dobrita, A., Yousefzadeh, A., Thorpe, S., Vadivel, K., Detterer, P., Tang, G., Schaik, G.-J. v., Konijnenburg, M., Gebregiorgis, A., Hamdioui, S. & Sifalakis, M.https://doi.org/10.1109/TCASAI.2024.3491673Energy-efficient SNN Architecture using 3nm FinFET Multiport SRAM-based CIM with Online Learning (2024)In Proceedings of the 61st ACM/IEEE Design Automation Conference, DAC 2024 (pp. 1-6). Article 260 (Proceedings - Design Automation Conference). IEEE. Huijbregts, L., Liu, H. H., Detterer, P., Hamdioui, S., Yousefzadeh, A. & Bishnoi, R.https://doi.org/10.1145/3649329.3656514Invited: Neuromorphic Vision Modalities in the NimbleAI 3D Chip (2024)In Proceedings of the 61st ACM/IEEE Design Automation Conference, DAC 2024 (pp. 1-4). Article 358 (Proceedings - Design Automation Conference). IEEE. Iturbe, X., Linares-Barranco, B., Ieng, S. H., Erdmann, A., Peres, L., Rhodes, O., Tornero, R., Sifalakis, M., Van De Burgwal, M., Yousefzadeh, A., Kooli, M., Alidori, R. & Zaykov, P.https://doi.org/10.1145/3649329.3689622Multidie 3-D Stacking of Memory Dominated Neuromorphic Architectures (2024)IEEE transactions on very large scale integration (VLSI) systems, 32(11), 2144-2148. Giacomini Rocha, L. M., Bilgic, R., Naeim, M., Das, S., Oprins, H., Yousefzadeh, A., Konijnenburg, M., Milojevic, D., Myers, J., Ryckaert, J. & Biswas, D.https://doi.org/10.1109/TVLSI.2024.3421625Overcoming the Limitations of Layer Synchronization in Spiking Neural Networks (2024)[Working paper › Preprint]. ArXiv.org. Koopman, R., Yousefzadeh, A., Shahsavari, M., Tang, G. & Sifalakis, M.https://doi.org/10.48550/arXiv.2408.05098Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification (2024)[Working paper › Preprint]. ArXiv.org. Xu, Y., Tang, G., Yousefzadeh, A., de Croon, G. C. H. E. & Sifalakis, M.https://doi.org/10.48550/arXiv.2407.20421Co-optimized training of models with synaptic delays for digital neuromorphic accelerators (2024)In ISCAS 2024 - IEEE International Symposium on Circuits and Systems (Proceedings - IEEE International Symposium on Circuits and Systems). IEEE. Patiño-Saucedo, A., Meijer, R., Detteter, P., Yousefzadeh, A., Garrido-Regife, L., Linares-Barranco, B. & Sifalakis, M.https://doi.org/10.1109/ISCAS58744.2024.10558209Eon-1: A Brain-Inspired Processor for Near-Sensor Extreme Edge Online Feature Extraction (2024)[Working paper › Preprint]. ArXiv.org. Dobrita, A., Yousefzadeh, A., Thorpe, S., Vadivel, K., Detterer, P., Tang, G., van Schaik, G.-J., Konijnenburg, M., Gebregiorgis, A., Hamdioui, S. & Sifalakis, M.https://doi.org/10.48550/arXiv.2406.17285Trip: Trainable Region-of-Interest Prediction for Hardware-Efficient Neuromorphic Processing on Event-based Vision (2024)[Working paper › Preprint]. ArXiv.org. Arjmand, C., Xu, Y., Shidqi, K., Dobrita, A. F., Vadivel, K., Detterer, P., Sifalakis, M., Yousefzadeh, A. & Tang, G.https://doi.org/10.48550/arXiv.2406.17483

Onderzoeksprofielen

Funded projects: 

  1. NeAIxt (2025): Next Generation of edge AI crossing technology fields
  2. TIRAMISU(2024): Training and Innovation in Reliable and Efficient Chip Design for Edge AI
  3. NEUROKIT2E(2023): Open-source deep learning platform dedicated to Embedded hardware and Europe
  4. REBECCA(2023): Reconfigurable Heterogeneous Highly Parallel Processing Platform for safe and secure AI
  5. NimbleAI(2022): Ultra-energy efficient and secure neuromorphic sensing and processing at the endpoint

PhD Students: 

  1. Sameed Sohail: Embedded Neuromorphic Processor Architecture with On-Device Adaptation

Master students: 

  1. Bram Bremer: Real-time acoustic imaging on an FPGA using recurrent neural networks
  2. Arjan Blankestijn: Accelerating Transformers on ZynQ platforms
  3. Sharon Moolenaar: Optimizing Network on chip for neuromorphic processors
  4. Mattias Westerink: Designing co-processor for RISC-V-based neuromorphic system
  5. Wiebren Wijnstra: Optimizing RISC-V processor for neuromorphic workloads
  6. Wim Nijsink: Measuring the reliability of existing neuromorphic solutions
  7. Haoran Wolfgang: Low latency hardware accelerator for sparse convolutional recurrent network toward neuromorphic object detection
  8. Ivan Knunyants: Optimizing transformer neural networks for event-driven inference in hardware
  9. Yashwanth Gopinath: Open-source RISC-V-based neuromorphic processor
  10. Roel Koopman (2024): Overcoming the Limitations of Layer Synchronization in Spiking Neural Networks
  11. Cina Arjmand (2023): Trainable Region of Interest Prediction: Hard Attention Framework for Hardware-Efficient Event-Based Computer Vision Neural Networks on Neuromorphic Processors  
  12. Lucas Huijbregts (2023): Transposable Multiport SRAM-based In-Memory Compute Engine for Binary Spiking Neural Networks in 3nm FinFET
  13. Shenqi Wang (2023): Hardware Efficient Object Detection for High Spatial Resolution Event Camera
  14. Refik Can Bilgiç (2023):  Analytical Modelling of 3D System Partitioning
  15. Pietro Martinello (2023): Forging a Multimodal Dataset: Uniting Diverse Sensor Data for Enhanced Analysis
  16. Roy Meijer (2023): Efficient Synaptic Delay Implementation in Digital Event-Driven Neuromorphic Processors
  17. Kevin Shidqi (2022): Benchmarking and Algorithm Optimization for SENeCA, a RISC-V-based Neuromorphic Processor
  18. Alexandra-Florentina Dobrit (2022): Brain-inspired feature extraction for near sensor extreme edge processing with Spiking Neural Networks
  19. Prithvish Vijaykumar Nembhani (2022): Efficient mapping of large-scale SNN and rate-based DNN on SENeCA
  20. Preetha Vijayan (2021): Temporal Delta Layer: Exploiting Temporal Sparsity in Deep Neural Networks for Time-Series Data

Bachelor students:

  1. Mattijn Spitteler: Universal Software-Configurable Extender for Hydraulic Cylinder Controllers

Visiting students:

  1. Ethan Milon: Radar processing for smart office applications
  2. Mustafa Canitz: Event-based camera processing for smart office applications
  3. YingFu Xu (2022):  Implementation of bio-inspired Optimical flow algorithm in neuromorphic processor
  4. Alberto Patino-Saucedo (2022): Hardware-aware training of models with synaptic delays for digital event-driven neuromorphic processors
Scan de QR-code of
Download vCard