Jan 31st, 2014, 3:00 pm in Huxley 345

Machine Learning Applications: Empowering Medical Science Through Computing

Increasing computational power over the past decade has enabled the rapid development of a variety of new machine learning methods that primarily aim to analyse medical data, in order to offer extended insights about the inner workings of humans. Evidently, understanding the human body better can potentially aid the earlier diagnosis and treatment of certain diseases that have been troubling humans for many years now.

An inherent problem of medical data is their increased complexity and high dimensionality, which is essentially caused by the complicated design of the human body but is also a result of noise coming from the acquisition hardware. In this talk, we will demonstrate some recent machine learning methodologies for removing noise and extracting inference from medical data using linear and non-linear dimensionality reduction techniques along with a set of unsupervised and supervised classification algorithms. Moreover, we show how these techniques can be best applied in order to aid the diagnosis of different types of cancer and also help in understanding how the human brain works when we are performing various actions in our everyday life.

Loizos Markides is a PhD student in the Department of Computing at Imperial College of London in the group of Machine Learning and Intelligent Data. He is currently working in the area of pattern recognition and machine learning in functional MRI data analysis, with special interest in the decomposition of the fMRI signal to primary cognitive processes using unsupervised learning techniques, and the later use of this decomposition to build large-scale fMRI decoding systems. More about me→

Zena Hira is a PhD student in the Department of Computing at Imperial College London, in the group of Machine Learning and Intelligent Data. She currently works on applying unsupervised machine learning algorithms and statistical techniques on high dimensional cancer data, in order to find ways of reducing the dimensionality and correctly classify new examples. Part of her research is examining how different forms of prior knowledge will affect the performance of already existing algorithms. More about me→