IIT KANPUR MSR COGNITIVE SCIENCES INTERVIEW EXPERIENCE

Question

Total seat = Around 10

Interview taken by Prof Himanshu Yadav

Q1.Introduce yourself and tell your research interest

Q2.What is an Artificial Neural Network?

Q3.How does Backprogragation and Gradient Descent works?

Q4.Some question on Loss function, trigonometry and probability

Q5.How to compare two computional models?

Q6.What is a P600 waveform?

Q7.Explain Cross Validation in Machine Learning?

Q8.Why there is a need to split dataset into training and testing set? What's the main reason?

 

Advice given by sir to me :- In the field of AI/ML having theoretical knowledge is good but practical knowledge is more needed.

Comments

I just wanted to know based on ur observation of this interview ..

Q1) Means what kinds of practical knowledge ....are you taking about implementation part...i mean suppose u know K-mean clustering does he talking about implementing something about in real world project ?  

Q2) Let suppose someone have good understanding about Linear algebra , pprobability and calculus and some basic stuff of ML.Is it not suffiecient to procede in AI/ML .Does they expecting some good project in AI/ML for their selection ?

Q3) Lastly I wanted to ask what they actually wants based on ur experiences ?

---

Actually I was able to explaine basics like gradient descent, backgropagation, loss function , overfitting and underfitting , performance metrics etc.....but after sir verified that my basics were cleared he framed a question like this ..... "let's say you are working on a project and you are given two computational models how will you compare them" in this question I should have said we can calculate performance metrics like accuracy and precision of both models and compare them but during the interview maybe because of interview pressure this thought didn't come in my mind or may be I have less real world experience......

 

Professors of iits are very smart instead of saying questions directly like "how to calculate performance metrics of a model" they will twist and give a real life situation to test weather candidate have real world experience.