I have two topics that I really want to get involved in.

1) Confirming current research in chromosome structure while using machine learning to find relationships in genetic motifs. For instance, is function associated with how the genome condenses?

2) Developing novel Computer Vision algorithms to learn from small sample sizes and video using specialized equipment.

Maybe there is a common problem between 1) and 2) that I can study in depth, but these seem like very different projects.

Would it be feasible to apply for a Master's in Quantitative Genetics (+ Research Thesis) with electives in Machine Learning and Statistics, then apply for a PhD in Machine Learning? I have a double major in Math and Computer Science with a few electives in genetics.


Your approach sounds reasonable to me. Both problems do share some elements in common:

  • both operate on a larger data set, so efficient algorithms are needed.

  • both may profit from novel approaches to identify patterns

Both could be based on AI. I know greedy algorithms from traditional computing for genetic research as well as for vision. Why not trying that way with you specific ideas? As I did a PhD in high performance computing, I can recommend doing your way. You should have passion for your path; it may take a while.

Not the answer you're looking for? Browse other questions tagged or ask your own question.