Chang Gao

Dr Chang Gao is a Tenure-Track Assistant Professor at the Department of Microelectronics, TU Delft, who has achieved significant advancements in energy efficient artificial intelligence (AI) computation without sacrificing accuracy. By reducing the energy cost of AI, Gao’s innovations have laid the groundwork for wearable and portable devices, such as smart watches, shoes, and cardiac implants, and long-term robotic prosthesis control, to provide 24/7 monitoring to improve health outcomes and patients’ quality of life.

Rather than focussing on building biologically accurate neural network models, which can lead to high production costs and less accuracy on real-world tasks, Gao applied neuromorphic principles, sparse neuron firing and connectivity to transform deep recurrent neural networks into more cost-efficient forms. He continues to bridge the gap between artificial neural networks and spiking neural networks by applying brain-inspired neuromorphic principles to massively accelerate the computation of state-of-the-art deep neural network architectures while maintaining competitive accuracy on real-world tasks.

Gao was the Best Paper Award recipient of the 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, is a co-recipient of the 2020 Misha Mahowald Prize for Neuromorphic Engineering, and received the 2022 Mahowald Early Career Award for Neuromorphic Engineering. He also received the 2022 Marie-Curie Postdoctoral Fellowship for his project on portable radar systems powered by energy-efficient AI accelerators.