profile pic


PhD Doctor of Philosophy candidate

neuroscience, machine learning, writing

Project ideas

Project ideas are meant to help inspire student thinking about their own project. Students are in the driver seat of their research and are free to use any or none of the ideas shared by their mentors.

How do neural networks capture artistic style?

Generative adversarial networks (GANs) learn to generate output data that mimic the training data. For example, if you train a GAN on paintings by Van Gogh, it will learn to produce new images that look like the paintings it was trained on. I want to understand this phenomena by investigating the following questions: through reviewing previous research and direct experiment, what characteristics of data are GANs capable of learning? In other words, are there some data distributions, say the distribution of jazz solos by Miles Davis, that are harder for a GAN to imitate than others? What are the relevant features of the data that the GAN learns?

Coding skills

Python, MATLAB, JavaScript, CSS, HTML

Interested in working with expert mentors like Andrew?

Apply now