Supervisors: Dr Ben Mills
Co-Supervisor: James Grant-Jacob
Advances in lasers now allow the laser-based processing of almost any material. Innovation in this field is now therefore becoming heavily focussed on making existing processing techniques more precise and efficient.
Neural networks are a computing paradigm inspired by the biological neurons in the human brain. They offer the capability for learning directly from experimental data, and hence can be used to find solutions even when the problem is not understood by a human. Neural networks therefore offer a remarkable solution to the optimisation and control of laser machining, which itself is far from understood.
The team is combining state-of-the-art neural networks with high-precision femtosecond laser machining, with the objective of achieving repeatable and high-speed fabrication at resolutions well-below the diffraction limit.
This PhD will be focussed on the following synergistic aspirations: 1) convolutional neural networks for real-time control of laser machining, and 2) generative adversarial networks for simulating and predicting laser machining. Neural networks require large amounts of experimental data for training, and hence this PhD will therefore involve a mixture of experimental photonics and laser machining, experimental automation (Python), and programming and designing neural networks (Python/Tensorflow). The supervisors and research team are well versed in the above techniques, and hence training and support will be provided.