1
$\begingroup$

Context

I am a final year Bachelor of Mathematics student and next semester I will write my Bachelor thesis.
My interests are in Machine Learning (ML) and I will do a master in ML next year. More specific sub-fields I like are

  • Deep Learning
  • Computer Vision
  • Natural Language Processing
  • Reinforcement Learning

And my interests outside of ML and mathematics include

  • Self-driving cars (e.g. Tesla)
  • Rocket and space exploration

more vaguely, I find tech interesting as a whole.

Question

I am looking for a thesis which would bring me as close as possible to the field of ML. Do you have topic recommendations ?

BUT my Bachelor is in Mathematics therefore I shall not write a thesis in Computer Science as it would not be accepted by my study director.

Some thoughts

I know some people who were in my case. One of them for instance discovered and proved some convergence results in the context of Gradient Descent. Maybe this will inspire you with your answers.

Thanks in advance!


PS: This is a duplicate of my original question on the Math Stack Exchange but I thought that people on the Computer Science Stack Exchange could bring a different point of view.

$\endgroup$
4
  • 1
    $\begingroup$ Sorry, StackExchange is not the site for this sort of question. I'm surprised you got an answer at math.SE. This question has two issues: 1. it's too localized based on your interests, it's unlikely to be useful to others, but more importantly 2. it's primarily opinion based, there is no right or wrong answer. $\endgroup$ – orlp Dec 30 '20 at 15:35
  • $\begingroup$ Thank you for your opinion. For 1), I think these interests are likely to also apply to other people looking for ideas for a thesis. For 2), I am looking for ideas so even though there is no right or wrong answer, an answer will be right if it helps me finding a thesis in the end. $\endgroup$ – Joris Limonier Dec 30 '20 at 15:58
  • 1
  • $\begingroup$ Welcome to Computer Science! Unfortunately, your question is not a good fit for the Stack Exchange format. We prefer questions that have objectively correct answers that will be useful both to the asker and others who have the same question in the future. What is or is not a suitable topic for study, projects or research is very much a matter of opinion and depends crucially on the interests and skills of the person who will be doing the work and the support that will be available to them. This is a question that you should be asking your professors. $\endgroup$ – D.W. Dec 31 '20 at 7:54
1
$\begingroup$

I would like to make two points clear as a researcher:

  1. Mathematics is a very broad discipline. When you're on bachelor level it is still appropriate to call it "Mathematics" but already in Masters, you'll need to specialize! Youll have to choose a branch and then you won't be "a mathematician" you'll be Statistician, a topologist, graph theorist, category theorist etc. This being said you need to ask yourself which branch you're most interested in? This leads to the next point:

  2. The fact that you're interested in Machine Learning already narrows it down to Probability & Statistics, Linear Algebra, Multivariate Calculus. And here I would say that any topic that falls within these categories will help you later along the road.

Bachelor Thesis is a piece of scientific work that's why it is called "Bachelor". You are supposed to do research and produce new knowledge regardless of how small or significant it will be. This forum cant do it for you.

Pick something YOU are interested in from Probability & Statistics, Linear Algebra or Multivariate Calculus and explore the topic. Once you start you'll inevitably get questions that need addressing. If you get stuck pick a classic problem (for example Knight's tour) and systematically break it down.

$\endgroup$
1
  • $\begingroup$ Thank you, that is some useful piece of advice, which I will follow. $\endgroup$ – Joris Limonier Dec 31 '20 at 16:17

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