Q1. How do you choose which ml model to use?
Q2. what is correlation(explain without referring ML)?
Q3. what does KNN do during training?
Q4. does pooling in CNNs have any learning?
Q5. what is a logarithm? (in linear algebra) what is it's significance and what purpose does it serve?
Q6. what are p-values? explain it in plain english without bringing up machine learning?
Q7. how are LSTMs better than RNNs? what makes them better? how does LSTMs do better what they do better than vanilla RNNs?
Q8. why does optimisers matter? what's their purpose? what do they do in addition to weights-updation that the vanilla gradient and back-prop does?
Q9. Explain eign vectors and eign values? what purpose do they serve in ML?
Q10. How to find the number of white cars in a city?
