Interviewer called me on the phone and asked a very dumb question regarding data preprocessing. Usually it should go from easy to complicating it but he didn't let me complete the code and started introducing complexities just when we hit them and was pretty intimidating to go through.
What is your NLP experience?
They asked about past projects and your experience
Task on developing ML model and deployment
Train ML models using iris flower data set
Typical questions about your background
Can you describe how XGBoost work?
Popular ML components like LSTMs, Transformers, CNN etc. Building ML models in the context of speech recognition/NLP and advantages or shortcomings of each approach. These have to all be addressed while building an ML pipeline. Know your own projects in detail and why certain models were used vs. others
Regularization, Over-fitting, Unbalanced data, ResNet, CNNs, C++ Inheritance
Your solutions to improve the code retrieval system
Viewing 7421 - 7430 interview questions