Zilverling

A. Yousefzadeh PhD (Amirreza)

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

I joined the University of Twente in February 2024 as an Assistant Professor in the field of edge AI. My focus is on designing embedded AI and neuromorphic systems. 

Brief CV:

  • Ph.D. in neuromorphic engineering at IMSE, Thesis: Digital Design For Neuromorphic Bio-Inspired Vision Processing
  • 2018-2020 (Netherlands): In the GrAI Matter Labs startup, later acquired by Snap, I mainly worked on the architecture of the NeuronFlow processor
  • 2020-2024 (Netherlands): In imec, at the Hardware Efficient AI group, I mainly worked on the architecture of the SENECA processor
  • 2024-Present: Assitant professor, Computer Architecture for Embedded Systems

Expertises

  • Computer Science

    • Neural Network
    • Synaptic Weight
    • Computer Hardware
    • Design-Space Exploration
    • Hardware Accelerator
    • Memory Footprint
    • Hardware Structure
    • Convolutional Neural Network

Organisaties

Research experiences:

  • Neuromorphic Sensing and processing
  • Embedded AI

I extensively use digital hardware design tools and gate-level simulations to co-optimize hardware architectures with neural network algorithms. Some of my technical experiences:

  • Design of programmable neuromorphic processors for embedded AI applications
  • On-device learning algorithms and hardware accelerators
  • Bio-inspired vision processing
  • Benchmarking and comparison of various algorithm optimizations in hardware

Please get in touch with me if you want to do a project in this field.

Publicaties

2024

Co-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/ISCAS58744.2024.10558209Hardware-aware training of models with synaptic delays for digital event-driven neuromorphic processors (2024)[Working paper › Preprint]. ArXiv.org. Patino-Saucedo, A., Meijer, R., Yousefzadeh, A., Gomony, M.-D., Corradi, F., Detteter, P., Garrido-Regife, L., Linares-Barranco, B. & Sifalakis, M.https://doi.org/10.48550/arXiv.2404.10597Optimizing event-based neural networks on digital neuromorphic architecture: a comprehensive design space exploration (2024)Frontiers in Neuroscience, 18. Article 1335422. Xu, Y., Shidqi, K., van Schaik, G. J., Bilgic, R., Dobrita, A., Wang, S., Meijer, R., Nembhani, P., Arjmand, C., Martinello, P., Gebregiorgis, A., Hamdioui, S., Detterer, P., Traferro, S., Konijnenburg, M., Vadivel, K., Sifalakis, M., Tang, G. & Yousefzadeh, A.https://doi.org/10.3389/fnins.2024.1335422

Onderzoeksprofielen

Funded projects: 

  1. TIRAMISU(2024): Training and Innovation in Reliable and Efficient Chip Design for Edge AI
  2. REBECCA (2022): Reconfigurable Heterogeneous Highly Parallel Processing Platform for safe and secure AI
  3. NEUROKIT2E (2022): Open-source deep learning platform dedicated to Embedded hardware and Europe

PhD Students: 

  1. Embedded Neuromorphic Processor Architecture with On-Device Adaptation (soon)

Master students: 

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

Bachelor students:


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