paid

Companies: Amazon, Google Difficulty: Easy Frequency:  Medium Question What is batch normalization and why is it useful? Answer Taken from Neural Network. Batch normalization can be thought of as the equivalent to…

Companies: Google Difficulty: Hard Frequency:  Low Question If you don’t use gradient descent or its derivaties, is there any way to optimize the model? Answer The question is asking us to think…

Companies: Google Difficulty: Medium Frequency:  Low Question What is the relationship between cross entropy and MLE? Answer For maximum likelihood estimation (MLE), it estimates the parameters of a probability distribution by maximizing…