I have a few math courses to pick from in my studies, and I would love some insights on which math courses from the following list are the most relevant for machine learning. I will note - to avoid this question being closed on "opinion based" cause, that my question does not involve which math courses I like or interests me, but being objectively as possible - which math courses are the most relevant for machine learning.

This are the following courses I can choose from:

  1. Numerical Analysis
  2. Ordinary Differential Equations 1
  3. Topology
  4. Theory of Functions of a Complex Variable 1
  5. Linear Algebra 3
  6. Number Theory
  7. Probability for Sciences

Since I know Linear Algebra and Probability are very important for Machine Learning, I will note that I have already studied Linear Algebra 1 and 2 (which include matrices, linear transformations, linear and bilinear operators, normed vector spaces, eigenvalues and eigenvectors, diagonalization, Jordan form, hermitian spaces, unitary and orthogonal transformations, and some more subjects), while Linear Algebra 3 syllabus' is mainly about groups, isomorphism theorems, Lagrange's theorem, group actions, Sylow's theorems, finitely generated Abelian groups, solvable groups, the symmetric group and free groups.

Also, I already had Probability 101 which is mainly discrete probability and includes basic probability theory, discrete distributions (such as Poisson, binomial, HG and more), random variables, markov's and Chebyshev's inequalities, expected value, variance and covariance, CLT and Markov chains, while the "Probability for Sciences" course has in its syllabus continues distributions, PDF, MGF, convergence of random variables and convergence in probability, the multi-dimensional normal distribution and some more subjects.

I will also note I have studied the following math courses as well: Calculus 1 and 2 and Discrete Math.


  • $\begingroup$ 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. $\endgroup$
    – Raphael
    Aug 2 '17 at 18:54

By far the most important in that list is probability -- learn as much probability as you can. Numerical analysis might also be of a little bit of use. The others probably won't be directly relevant to most of the practice of machine learning, but hey, become more comfortable with mathematics is probably useful in general.

  • $\begingroup$ Thanks for the answer! so Continuous Probability is important for Machine Learning? I somehow thought that discrete probability is more relevant and continuous is less. And please correct me if I'm wrong, but number theory is less relevant to machine learning, but very relevant to computer science in general, and especially for cryptography , am I right? $\endgroup$
    – Mickey
    Aug 4 '17 at 17:18

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