PhD in Psychology: Machine learning and sleep – detecting neural replay in sleep with EEG classifiers

Outline

Memories are spontaneously replayed in sleep, and this replay is critical for their consolidation (strengthening and integration with pre-existing knowledge).

Until recently, it has been impossible to detect these replays in humans, but work from our laboratory has devised a method to achieve this using machine learning to analyse EEG data.

In this PhD, we will seek to extend this work by improving the detection method and using it to examine many additional aspects of memory replay such as how long it lasts, which phases of sleep it occurs in, and how it impacts on neuroplasticity.

We will first use common machine learning algorithms such as SVM, Logistic Regression, KNN with emphasis in feature extraction and selection.

As this is a challenging problem, we aim to explore and combine techniques from areas such as time series analysis (dynamic time warping), neuroimaging (representation similarity analysis) and deep learning (LSTM, convolutional NN).

We seek a computer science or engineering student with a good background in machine learning and signal processing to take this work forward.

What is funded

Full UK/EU tuition fees and Doctoral stipend matching UK Research Council National Minimum.

Duration

3 Years

Eligibility

Full awards (fees plus maintenance stipend) are open to UK Nationals, and EU students who can satisfy UK residency requirements. To be eligible for the full award, EU Nationals must have been in the UK for at least three years prior to the start of the course for which they are seeking funding, including for the purposes of full-time education.