Nothing that difficult.
Machine Learning Interviews
Machine Learning Interview Questions
"To get a job in machine learning, you must have the programming and mathematical knowledge to create artificial intelligence that is capable of learning new tasks without being explicitly coded. In an interview you may be asked about your experience with pertinent coding languages such as Java and C++ as well as with writing algorithms. The interview will be comprised mainly of technical questions that test your knowledge of the fundamental concepts of machine learning such as data mining and signal processing."
8,221 machine learning interview questions shared by candidates
What is overfitting and underfitting in regression? How to deal with it?
In a classification problem, if the classes are biased, what should you do?
Go through with your resume.
Some commonly seen Leetcode problems, like dynamic programming and two pointers. No job-specific questions at that time
What is regularization? L1 or L2 regularization? What is PCA?
Coding question: Write a multihead attention class. Follow-up questions: what to do to make the input and output dimensions of the tensor different, explaining the code.
Can you explain your approach to solve a complex problem?
Some questions about optimization techniques, e.g. convergence of gradient descent/Newton's method, how would you find a global optimum with an iterative technique.
Questions on resume projects, mostly on deep learning and probabilistic graphical models - variational auto encoders, back propagation.
Viewing 3161 - 3170 interview questions