Organisation profile

Organisation profile

The focus of the Machine Learning in Photonic Systems Group at DTU Electro is on the development and application of machine learning techniques to advance photonic classical and quantum measurement, communication and sensing systems.

Our society relies heavily on information and communication infrastructure. To sustain the growth of our society we therefore need to be able to satisfy future data demands. This is a challenging task as current technology cannot keep up with future data demands.

A paradigm shift is needed to conceptualize novel systems that will be able to satisfy not only future data rate demands, but also provide high-energy efficiency.

Machine learning for efficient data transmission

The overall goal is to introduce some degree of intelligence to photonic systems to enable future generation of systems that can provide robust transmission, secure data transmission, and maximum theoretically achievable sensitivity and power efficiency.

We work on the development of efficient algorithms for the training of learning machines as well as on experimental demonstrations. So far, we have been able to demonstrate that machine learning enables record sensitivity in terms of phase and relative intensity noise measurements of laser and frequency comb sources. Moreover, we have shown that by using machine learning we enabled optimization arbitrary gain profiles wideband amplifiers are feasible.

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. Our work contributes towards the following SDG(s):

  • SDG 7 - Affordable and Clean Energy
  • SDG 13 - Climate Action


Dive into the research topics where Machine Learning in Photonic Systems is active. These topic labels come from the works of this organisation's members. Together they form a unique fingerprint.

Collaborations and top research areas from the last five years

Recent external collaboration on country/territory level. Dive into details by clicking on the dots or