Federico Corradi

Federico Corradi

Professor in Neuromorphic Computing & Engineering

Eindhoven University of Technology (TU/e)

I take inspiration from neural systems' extraordinary information processing abilities to design more robust, adaptable, and energy-efficient microchips. My work focuses on developing brain-inspired, ultra-low-power systems, advancing our understanding of distributed information processing, and addressing real-world challenges through innovative solutions.

Research / NECS Lab

Neuromorphic Edge Computing Systems

My research centers on neuromorphic computing and engineering, spanning computational model development to microelectronic architecture design. I apply brain-inspired principles to create energy-efficient sensing and computing technologies with applications in robotics, machine vision, temporal signal processing, and biomedical analysis.

Bio-inspired Algorithms & Neuromorphic Computing

Developing spiking neural network models and brain-inspired learning algorithms implemented on FPGA platforms. Exploring adaptive, recurrent architectures for time-domain classification and online learning.

FPGA SNN Learning Rules

Energy-Efficient Hardware

Designing ultra-low-power ASICs and edge-AI accelerators for neuromorphic workloads. Chip design in Skywater 130nm and advanced nodes, targeting orders-of-magnitude efficiency gains over conventional processors.

Edge-AI ASIC Low Power

Event-based Sensing & Biomedical Signal Processing

Leveraging event-driven cameras and sensors combined with spiking neural networks for efficient real-time processing. Applications in radar-camera fusion, gesture recognition, and biomedical signal analysis.

DVS Radar Biomedical

Projects

MicroBrain

Micro-scale brain-inspired computing architectures for ultra-low-power edge intelligence.

Neuromorphic Hardware

SpikeVision

Event-based vision processing with spiking neural networks for real-time object detection and tracking.

Event Camera SNN

Radar-SNN

Radar signal processing with spiking neural networks for gesture recognition and human activity detection.

FMCW Radar SNN

Keyword Spotting SNN

Energy-efficient keyword spotting using spiking neural networks for always-on edge devices.

Audio Edge-AI

Local Learning

Local learning rules for neuromorphic systems enabling on-chip adaptation without backpropagation.

Learning Rules On-chip

SNN Transformer

Spiking neural network transformer architectures combining attention mechanisms with spike-based computation.

Transformer SNN

Skywater 130nm Chips

Open-source analog and mixed-signal neuromorphic chip designs using the Skywater 130nm PDK.

aVLSI Open Source

Genomics-SNN

Applying spiking neural networks to genomics data analysis and biological sequence processing.

Genomics SNN

BioSNN

Exploiting spiking neural networks and event-based coding for efficient processing of biological signals (ECG, EEG) at the edge.

Biomedical ECG EEG Edge-AI

Career

0+ Citations
0 h-index
0 i10-index
2022 — Present

Assistant Professor

Eindhoven University of Technology (TU/e)

Department of Electrical Engineering, Electronic Systems group. Leading the NECS Lab on neuromorphic edge computing systems.

2019 — 2022

Senior Research Scientist

IMEC, Netherlands

Ultra-low-power systems for IoT. Designed neuromorphic processing architectures for edge computing applications.

2015 — 2018

PostDoc & Research Scientist

University of Zurich & Inilabs GmbH

Neuromorphic engineering research at the Institute of Neuroinformatics. Development of event-driven sensing systems.

2015

PhD NeuroInformatics & Neuroscience

University of Zurich & ETH Zurich

International PhD from the ETH Neuroscience Centre Zurich, Institute of Neuroinformatics.

2010

MSc Physics cum laude

Sapienza University of Rome

2007

BSc Physics

University of Parma

Teaching

Neuro Computation

2022 — 2026

Fundamentals of neural computation, spiking neural networks, and brain-inspired algorithms. Covers neuron models, learning rules, and neuromorphic hardware principles.

Intelligent Architectures

2022 — 2026

Design principles for intelligent hardware architectures. Topics include FPGA-based accelerators, neural network hardware implementation, and energy-efficient computing systems.

Featured Publications

226 citations

Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks

Nature Machine Intelligence, 2021

95 citations

μBrain: Event-Driven and Fully Synthesizable Architecture for Spiking Neural Networks

Frontiers in Neuroscience, 2021

60 citations

Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time

Nature Machine Intelligence, 2023

Datasets

Aircraft Marshaling Signals Dataset

FMCW Radar & Event-Based Camera fusion dataset for aircraft marshaling signal recognition.

Radar Event Camera Multimodal

jAER

Java AER — first published version of the open-source framework for address-event representation processing.

AER Open Source

Patents

US Patent

Radar Detection Sensor, System, and Method

US Patent App. 17/998,532 — 2023

EU Patent

Controlling Neuron Firing in a Spiking Neural Network

EP 22214325.7 — Filed Dec 16, 2022

EU Patent

Radar Detection Sensor, System, and Method

EP 3910369A1 — Filed May 13, 2020

Contact

Office

Flux Building, Room 4.130

Eindhoven University of Technology

Phone

+31 (0)40 247 2556

Consultancy

Available for consulting in neuromorphic engineering, edge-AI hardware design, and spiking neural network solutions.

KvK registration: 94271437

Editorial & Service

Review editor for Frontiers in Neuromorphic Engineering, IEEE, IOP Science. Editorial board member, Microprocessors and Microsystems.