The Efficient Machine Intelligence (EMI) research lab @ TU Delft focuses on neuromorphic algorithm-hardware co-design for energy-efficient edge intelligence. 

April 30, 2025

Congratulations to our PhD student, Ang Li, who received the 2025 IEEE Circuits and Systems Student Travel Grant for his oral presentation: "DPD-NeuralEngine: A 22-nm 6.6-TOPS/W/mm2 Recurrent Neural Network Accelerator for Wideband Power Amplifier Digital Pre-Distortion" at ISCAS 2025.​

​

March 21, 2025

1️⃣ Full-Custom Digital ASIC Design for Edge AI Computing

Develop energy-efficient AI chips for healthcare (e.g., next-gen hearing aids) and IoT devices. Ideal candidates have experience in full-custom ASIC design (Verilog/SystemVerilog, Cadence/Synopsys tools) and an interest in digital in-memory computing or non-von Neumann architectures.

2️⃣ Algorithm-Hardware Co-Design for AI-Enhanced Transceivers

Revolutionize wireless systems (5G/6G, automotive) using AI for power amplifier linearization and interference cancellation. Collaborate with NXP Semiconductors (Robert van Veldhoven & Maarten Molendijk). Requires knowledge of neural networks, signal processing (Python/MATLAB), and RF systems.

We offer:

• 4-year full funding (€2,901–€3,707/month)

• Access to TU Delft/NXP facilities and industry networks

• Mentorship in a dynamic, interdisciplinary team

Apply by April 25, 2025

Submit your CV, transcripts, thesis, and references to Dr. Chang Gao: chang.gao@tudelft.nl

March 10, 2025

We are thrilled to announce our new collaboration with NXP Semiconductors to tackle the future of high-performance Analog-to-Digital Converters (ADCs) by harnessing machine learning to calibrate impairments and boost efficiency. Backed by €681,434 and running through October 31, 2028, this Holland High Tech-supported project reflects our mission to accelerate microelectronics innovation. Expect exciting progress as we redefine what’s possible in ADC design.

Read more about this project: https://hollandhightech.nl/en/programmes-and-projects/projects/machine-learning-calibrated-adc

Feb 15, 2025

We are thrilled to announce that our EMI Research Group’s brilliant students have achieved remarkable success at this year’s flagship IEEE conferences!

A huge congratulations to our PhD students, Ang Li, Yizhuo Wu, Yi Zhu (Ampleon), and MSc students Sjoerd Groot, Huanqiang Duan, Haolin Wu, Manno Versluis, and Kun Qian for their exceptional work.

• DeltaDPD: Exploiting Dynamic Temporal Sparsity in Recurrent Neural Networks for Energy-Efficient Wideband Digital Predistortion (Y. Wu, Y. Zhu, K. Qian) was accepted to the 2025 IEEE MTT-S International Microwave Symposium (IMS) and recognized as one of the IMS Top 50 Papers, with an invitation to present at IEEE MWTL. This work is a collaboration between EMI and Ampleon Netherlands B.V.

• TCN-DPD: Parameter-Efficient Temporal Convolutional Networks for Wideband Digital Predistortion (by H. Duan) also earned acceptance at IMS 2025.

• At the 2025 IEEE International Symposium on Circuits and Systems (ISCAS), our team’s DPD-NeuralEngine: A 22-nm 6.6-TOPS/W/mm² Recurrent Neural Network Accelerator for Wideband Power Amplifier Digital Pre-Distortion (by A. Li, H. Wu with equal contribution), supported by GlobalFoundries and CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning (by S. Groot) were accepted.

These achievements underscore the innovation, dedication, and impact of our research. Join us in congratulating our students for advancing the state-of-the-art in digital predistortion and speech denoising. We are immensely proud of your hard work and success!

July 18, 2024

Dr. Chang Gao has been awarded a prestigious Veni grant of €320,000 from the Dutch Research Council (NWO) for the project "Energy-Efficient Real-Time Edge Intelligence for Wearable Healthcare Devices." This innovative research aims to develop new software and hardware technology to enhance the intelligence and efficiency of wearable healthcare devices like eye movement trackers, hearing aids, and heart rate monitors. By processing data and running AI algorithms directly on these devices using specialized hardware accelerators, the project seeks to enable instant health monitoring, improve privacy, and reduce energy consumption. This work could transform personal health monitoring, making it faster, more secure, and widely accessible while contributing to the development of smarter, more sustainable wearable devices.

May 29, 2024

Congratulations to Qinyu Chen (Assistant Prof. @ Leiden Univ.) and Chang Gao (Assistant Prof. @ TU Delft) for their paper at ISCAS 2024. The paper is titled "Epilepsy Seizure Detection and Prediction using an Approximate Spiking Convolutional Transformer." The paper won the Best Paper - Honourable Mention Award from the IEEE ISCAS Neural Systems and Application Technical Committee (NSATC).

April 17, 2024

We're thrilled to announce our collaboration with GlobalFoundries in the GF 12LP+ University Partnership Program to support our research on Low-Power AI Hardware Accelerators using the cutting-edge 12 nm technology for enabling energy-efficient signal processing in transmitters for future wireless communications technologies and potentially useful for many other applications such as augmented reality and wearable healthcare.

Feb 2, 2024

The premier International Microwave Symposium (IMS) has accepted our paper "MP-DPD: Low-Complexity Mixed-Precision Neural Networks for Energy-Efficient Digital Pre-distortion of Wideband Power Amplifiers," mainly done by our PhD students Yizhuo Wu and Ang Li. The paper was ranked in the Top 50 and invited to the IEEE Microwave and Wireless Technology Letters. This paper proposes a novel DPD with Fixed-Point-Floating-Point Mixed-Precision parameters and intermediate states, which can reduce DPD inference power consumption by 2.6X on 160MHz 1024-QAM OFDM signals without losing linearization performance (-38dB EVM).

MP-DPD is trained using our recently released OpenDPD framework, available at https://github.com/lab-emi/OpenDPD.

Jan 19, 2024

We are thrilled to release OpenDPD: An Open-Source PyTorch-based End-to-End Learning & Benchmarking Framework for Wideband Power Amplifier Modeling and Digital Pre-Distortion (DPD). Authored by Yizhuo Wu, Gagan Deep Singh, Mohammad Reza Beikmirza, Leo de Vreede, Morteza Alavi, and Chang Gao (https://arxiv.org/abs/2401.08318). DPD enhances signal quality in wideband RF power amplifiers (PAs) and is a critical module in future 6G or Wi-Fi 7 wireless communication systems. OpenDPD comes with a free digital power amplifier I/Q dataset for you to train and benchmark machine learning (ML)/artificial intelligence (AI)-based DPDs and fairly compare them with other works. We will collaborate closely with our industrial partners to update this infrastructure periodically. OpenDPDv2 will come later this year with also free analog PA datasets.

OpenDPD code, datasets, and documentation are publicly available at https://github.com/lab-emi/OpenDPD. This work will be presented as a lecture at the 2024 IEEE International Symposium on Circuits and Systems (ISCAS), Singapore, in the Special Session: RFIC & AI: Pioneering New Wireless Communications.