Highlighting women’s contribution to the HYBRAIN project – Interview with Yuhan He

Interview with Yuhan He, University of Oxford.

Can you introduce yourself?

I am Yuhan He, a final-year DPhil student from Prof. Harish Bhaskaran’s group at University of Oxford. I obtained my BEng degree in electronic engineering and my current research focuses on the hardware implementation for energy-efficient photonic computing.

Can you share with us the story/reason that led you to decide to become a researcher?

I explored various opportunities to find my passion during my undergraduate years.

One pivotal experience was participating in a student research program under the guidance of Prof. Huanglong Li, where I delved into the field of electrical in-memory computing.

His passion and dedication to research left a profound impression on me and inspired me to consider a similar path.

Later experiences as an exchange student at Qutech Delft and a summer visiting student at my current group further confirmed my decision to pursue a PhD.

Through these experiences, I realized how much I enjoy the process of experimentation and discovery, especially in the field of computing systems, which continues to fuel my curiosity.

What are the domains that your research is focusing on?

AI, Photonic computing, In-memory computing, Digital hardware design.

Why did you decide to focus on these domains, what do you like about them?

I have always been passionate about computing systems and enjoy experiments and hardware implementation.

My undergraduate experience introduced me to the field of electrical in-memory computing.

Comparatively, photonic computing is a newer and rapidly emerging area, offering exciting potential beyond electronic computing.

This motivated me to shift my PhD research focus toward photonic computing. I found these domains especially vital and promising in the AI-driven era.

About your work in HYBRAIN

What are you working on in HYBRAIN?

I am working on energy-efficient hardware implementations for photonic in-memory computing systems.

My main contributions include designing, simulating, fabricating, measuring, and analyzing energy-efficient, CMOS-compatible, phase-change material-based photonic devices.

I also contribute to the photonic layout design for foundry-run fabrication and the development of mixed-signal transceiver peripherals for the computing system.

What is the expected outcome/impact of your work?

My work aims to integrate the advantage of both electronics and photonics for in-memory computing systems, contributing to energy-efficient, high-throughput and low-latency solutions.

What is your specific personal contribution to these activities?

I am involved in the design of the near-memory digital logic of analog-in-memory computing. My main contribution is to design digital components, simulate and synthesise them.

What is the expected outcome/impact of your work?

My work will contribute to the possibility of using analog-in-memory computing systems in an increasing number of fields where high throughput, high accuracy, and reduced area are needed.

What do you like about the HYBRAIN project?

It is both innovative and vital.

HYBRAIN focuses on developing a hybrid electronic-photonic architecture, which has the potential to significantly enhance the capabilities of current digital computing systems by reducing power consumption and improving computational efficiency.

This is especially critical for real-world AI applications, where the demand for processing vast amounts of data at high speed and with minimal energy consumption continues to grow.

Hybrid architectures could pave the way for more scalable and sustainable AI systems.

More specifically, what do you like about working on HYBRAIN?

The most exciting aspect of working on HYBRAIN for me is the cross-disciplinary communication within the community.

There are experts from diverse backgrounds, including digital electronics, analog electronics, photonics, and materials science, as well as prestigious groups from both industry and academia.

It is a valuable opportunity for an early-career researcher to gain a comprehensive understanding of the entire field and contribute to advancing cutting-edge technology.

Your personal insights

What is the potential application for the HYBRAIN technology that excites you the most? Motivare your answer.

The application of HYBRAIN technology that excites me the most is its potential to advance AI agents.

By harnessing the energy-efficient, high-throughput, and low-latency hybrid electronic-photonic architecture, AI agents could become far more powerful, capable of handling increasingly complex, adaptive, and efficient tasks — in other words, offering highly personalized capabilities.

This would have a transformative impact on a variety of fields, including virtual training and healthcare.

With enhanced edge-processing capabilities, AI agents could deliver personalized learning experiences and contribute to tailored treatment plans.

Moreover, it could lower the barriers to cross-disciplinary learning and provide crucial support for early-warning systems to monitor and respond to individual health conditions.

In your opinion, why should AI and Edge Computing researchers pay attention to the HYBRAIN technology?

AI and Edge Computing organizations should pay attention to HYBRAIN technology because it represents a groundbreaking advancement in the integration of electronic and photonic systems.

By leveraging the hybrid electronic-photonic architecture, HYBRAIN offers significant advantages in terms of energy efficiency, high throughput, and low latency —characteristics that are crucial for AI and Edge Computing.

These advancements provide organizations with an opportunity to accelerate innovation and strengthen their position in the competitive landscape.

If HYBRAIN is successful in creating its technology, how do you think the AI and Edge Computing domains will change as a result of the uptake of HYBRAIN’s technology?

It will be a pivotal, even transformative, step for the AI and Edge Computing domains.

The HYBRAIN technology is expected to enhance computing performance by improving energy efficiency, increasing throughput and reducing latency.

These advancements will enable AI and Edge Computing systems to handle more complex tasks at the edge, becoming more responsive and adaptive.

This will facilitate real-time decision making and personalized experience, leading to the widespread adoption of AI applications and therefore driving innovation across multiple sectors.

What would be your advice for young women wishing to pursue their passion for AI, Edge Computing and other STEM domains with a research career?

Be brave.

Be brave enough to explore the fields that excite you.

Be brave to steer projects in directions you find meaningful despite resistance, and be brave to communicate openly with people.