13 Useful Deep Learning Interview Questions And Answer

Introduction To Deep Learning Interview Questions And Answer

Today Deep Learning is been seen as one of the fastest growing technology with a huge capability to develop an application which has been seen as tough some time back. Speech recognition, image recognition, finding patterns in a dataset, object classification in photographs, character text generation, self-driving cars and many more are just a few examples where Deep Learning has shown its importance.

So you have finally found your dream job in Deep Learning but are wondering how to crack the Deep Learning Interview and what could be the probable Deep Learning Interview Questions. Every interview is different and the scope of a job is different too. Keeping this in mind we have designed the most common Deep Learning Interview Questions and Answers to help you get success in your interview.

Below are few Deep Learning Interview questions which are frequently asked in Interview and would also help to test your levels:

Part 1 –Deep Learning Interview Questions (Basic)

This first part covers basic Deep Learning Interview Questions and Answers

1. What is deep learning?

Answer:
The area of machine learning which focuses on deep artificial neural networks which are loosely inspired by brains. Alexey Grigorevich Ivakhnenko published the first general on working Deep Learning network. Today it has its application in various fields such as computer vision, speech recognition, natural language processing.

2. Why are deep networks better than shallow ones?

Answer:
There are studies which say that both shallow and deep networks can fit at any function, but as deep networks have several hidden layers often of different types so they are able to build or extract better features than shallow models with fewer parameters.

3. What is a cost function?

Answer:
A cost function is a measure of the accuracy of the neural network with respect to given training sample and expected output. It is a single value, nonvector as it gives the performance of the neural network as a whole. It can be calculated as below Mean Squared Error function:-
MSE=1n∑i=0n(Y^i–Yi)^2
Where Y^ and desired value Y is what we want to minimize.

Let us move to the next Deep Learning Interview Questions.

4. What is a gradient descent?

Answer:
Gradient descent is basically an optimization algorithm, which is used to learn the value of parameters that minimizes the cost function. It is an iterative algorithm which moves in the direction of steepest descent as defined by the negative of the gradient. We compute the gradient descent of the cost function for given parameter and update the parameter by the below formula:-
Θ:=Θ–αd∂ΘJ(Θ)
Where Θ – is the parameter vector, α – learning rate, J(Θ) – is a cost function.

5. What is a backpropagation?

Answer:
Backpropagation is training algorithm used for multilayer neural network. In this method, we move the error from an end of the network to all weights inside the network and thus allowing efficient computation of the gradient. It can be divided into several steps as follows:-

Forward propagation of training data in order to generate output.
Then using target value and output value error derivative can be computed with respect to output activation.
Then we back propagate for computing derivative of error with respect to output activation on previous and continue this for all the hidden layers.
Using previously calculated derivatives for output and all hidden layers we calculate error derivatives with respect to weights.
And then we update the weights.

6. Explain the following three variants of gradient descent: batch, stochastic and mini-batch?

Answer:
Stochastic Gradient Descent: Here we use only single training example for calculation of gradient and update parameters.
Batch Gradient Descent: Here we calculate the gradient for the whole dataset and perform the update at each iteration.
Mini-batch Gradient Descent: It’s one of the most popular optimization algorithms. It’s a variant of Stochastic Gradient Descent and here instead of single training example, mini-batch of samples is used.

Data Scientist Course 43 Online Courses | 170+ Hours | Verifiable Certificates | Lifetime Validity Watch The Course Preview

Part 2 – Deep Learning Interview Questions (Advanced)

Let us now have a look at the advanced Deep Learning Interview Questions.

7. What are the benefits of mini-batch gradient descent?

Answer:
Below are the benefits of mini-batch gradient descent
•This is more efficient compared to stochastic gradient descent.
•The generalization by finding the flat minima.
•Mini-batches allows help to approximate the gradient of entire training set which helps us to avoid local minima.

8. What is data normalization and why do we need it?

Answer:
Data normalization is used during backpropagation. The main motive behind data normalization is to reduce or eliminate data redundancy. Here we rescale values to fit into a specific range to achieve better convergence.

Let us move to the next Deep Learning Interview Questions.

9. What is weight initialization in neural networks?

Answer:
Weight initialization is one of the very important steps. A bad weight initialization can prevent a network from learning but good weight initialization helps in giving a quicker convergence and a better overall error. Biases can be generally initialized to zero. The rule for setting the weights is to be close to zero without being too small.

10. What is an auto-encoder?

Answer:
An autoencoder is an autonomous Machine learning algorithm that uses backpropagation principle, where the target values are set to be equal to the inputs provided. Internally, it has a hidden layer that describes a code used to represent the input.
Some Key Facts about the autoencoder are as follows:-

•It is an unsupervised ML algorithm similar to Principal Component Analysis
•It minimizes the same objective function as Principal Component Analysis
•It is a neural network
•The neural network’s target output is its input

11. Is it OK to connect from a Layer 4 output back to a Layer 2 input?

Answer:
Yes, this can be done considering that layer 4 output is from previous time step like in RNN. Also, we need to assume that previous input batch is sometimes- correlated with current batch.

Let us move to the next Deep Learning Interview Questions.

12. What is a Boltzmann Machine?

Answer:
Boltzmann Machine is used to optimize the solution of a problem. The work of Boltzmann machine is basically to optimize the weights and the quantity for the given problem.
Some important points about Boltzmann Machine −
•It uses recurrent structure.
•It consists of stochastic neurons, which consist one of the two possible states, either 1 or 0.
•The neurons in this are either in adaptive (free state) or clamped (frozen state).
•If we apply simulated annealing on discrete Hopfield network, then it would become Boltzmann Machine.

13. What is the role of the activation function?

Answer:
The activation function is used to introduce non-linearity into the neural network helping it to learn more complex function. Without which the neural network would be only able to learn linear function which is a linear combination of its input data.

Recommended Articles

This has been a guide to List Of Deep Learning Interview Questions and Answers so that the candidate can crackdown these Deep Learning Interview Questions easily. You may also look at the following articles to learn more

1. Learn The Top 10 Most Useful HBase Interview Questions
2. Useful Machine Learning Interview Questions And Answer
3. Top 5 Most Valuable Data Science Interview Questions
4. Important Ruby Interview Questions And Answer