As a master’s student in statistics, I’m eager to take the next step and pursue a PhD in machine learning. My goal is to focus on the theoretical foundations of deep neural networks and eventually become a researcher at an AI research lab. But with so many fascinating areas to explore, I’m unsure which path to take.
I’m considering statistical learning theory or optimization as my PhD research area, but I want to make sure I’m making an informed decision. That’s why I’m reaching out for advice from those with more experience in the field.
If you’re working on the theoretical foundations of machine learning or deep learning, I’d love to hear your thoughts on the most promising areas of research. What techniques and mathematical frameworks are currently being used by researchers in this space?
Some specific questions I have include:
* What area(s) of research would you recommend for someone interested in doing fundamental research in machine learning/DNNs?
* What are the popular/promising techniques and mathematical frameworks used by researchers working on the theoretical foundations of deep learning?
Thanks in advance for your guidance and insights!