Google

There were 5 interviews: * 4 DSA rounds * 1 culture fitment round In each DSA round, you can be asked any number of questions, depending on your speed to solve the problems. In one of the rounds, I was asked 3 questions. Some rounds were very easy

Well, MLPs work great in classification problems. The reason we used CONV layers earlier is that MLPs lose a lot of valuable information when trying to extract features from the image, because we have to flatten the image before feeding it to the ne

It was good, but I messed it up. It started with a coding round. I got a tree and dynamic programming question, a variation of LCS. The platform was HackerEarth, and it was on campus.