Deep Learning for Mathematical Imaging: CMIT Research Summer Internship 2024

Published on

Summer intern students after their final presentation
Summer intern students after their final presentation.

The Centre for Mathematical Imaging Techniques (CMIT) ran again this summer an intern programme for undergraduate students on "deep learning for mathematical imaging”. The internship provides opportunities for Year 1-3 students to engage in hands-on research experience. This year, 22 students participated in the training, which was given by invited lecturers from Liverpool, Glasgow, Cambridge, Oxford, Edinburgh, Bath, and MathWorks. In the research part, students worked in small groups on implementing and testing deep learning approaches on current research problems in grain imaging (materials science), medical imaging, and image stylization.

We organized a series of online lectures on Python basics, deep learning with PyTorch, Google’s Colab, reinforcement learning, attention networks, generative adversarial networks (GANs), and machine learning basics with Matlab. Lectures were given by Dr. Andreas Alpers (UoL), Prof. Ke Chen (University of Strathclyde), Dr. Hongrun Zhang (University of Cambridge), Dr. Tao Du (University of Oxford), Dr. Maciej Buze (Heriot-Watt University), Dr. Liam Burrows (University of Bath), and Dr. George Amarantidis Koronaios (MathWorks). The students Kirsty Cowie, Yan Fang, Ruishu Jiang, Alistair Kerr, Jiawei Kong, Guogeng Sheng, Shengkai Sun, Yifan Wang, Zhe Wang, Menglei Zhang finished the planned projects, passed with distinction, and obtained a certificate. Congratulations!

Based on the positive experience and popular demand we will offer this internship again next summer to enable students to gain added experience in research in the fast-growing area of data science.