Python, R and SAS work really well for solving the predictive modelling and machine learning problems. The libraries like “sklearn” are sufficient for building regression models, trees, random forest and boosting models. But these tools have limited deep neural networks libraries. What are the tools/frameworks for deep learning algorithms?
TensorFlow – One of the most famous deep learning framework.
- TensorFlow was developed by the Google Brain team for internal use.
- It was released under the Apache 2.0 open source license on November 9, 2015
- Most popular among all Deep learning frameworks.
- TensorFlow works really well with matrix computations – All the deep learning algorithms are highly calculation intensive.
- Scalable to multi-CPUs and even GPUs
- Can handle almost all type of deep networks, be it ANN or CNN or RNNs
- Has Python API and python is very easy install and to work on.
- We can use numpy to build all the models from scratch. But TensorFlow does it better by providing function to do it easily.
- TensorFlow has one of the best documentation and great community support as of now.
- Keras is a wrapper on top of TensorFlow. High level API written in Python. Less lines of code
Below is a list of Interview questions on TensorFlow and Keras
Sr No |
Question |
Option A |
Option B |
Option C |
Option D |
Answer |
1 |
Which tool is best suited for solving |
R |
Sk-learn |
Excel |
TensorFlow |
D |
2 |
A tensor is similar to |
Data Array |
ANN Model |
SQL query |
Pythoncode |
A |
3 |
How calculations work in TensorFlow |
Through vector multiplications |
Through RDDs |
Through Computational Graphs |
Through map reduce tasks |
C |
4 |
In TensorFlow, what is the used of a |
The current work space session for storing |
We launch the graph in a session |
A session is used to download the data |
A session is used for exporting data out of |
B |
5 |
What does feed_dict do? |
Feeds external data into computational |
Creates a new place holder |
Creates a new tensor |
Creates a new session |
A |
6 |
out=tf.add(tf.matmul(X,W), b) |
Logistic Regression Equaltion |
Deep ANN equation |
Random Forest Equation |
Linear Regression equation |
D |
7 |
tf.reduce_sum(tf.square(out-Y)) |
Linear Model equation |
Maximum Entropy loss function |
Squared Error loss function |
Feed_dict process |
C |
8 |
How can we improve the calculation speed in TensorFlow, without losing accuracy? |
Using GPU |
By doing random sampling on Tensors |
By removing few nodes from computational |
by removing the hidden layers |
A |
9 |
Kears is a deep learning framework on which tool |
R |
TensorFlow |
SAS |
Azure |
B |
10 |
What is the meaning of model=sequentil() in Keras? |
No such code in Keras |
Keras should be used only for sequential |
Keras builds sequential models |
creates a computational graph |
C |
11 |
Which tool is NOT Suited for building |
Python |
TensorFlow |
Excel |
Keras |
C |
12 |
Can we have multidimentional tensors |
No tensor can have maximum two dimentions |
Possible only in image data |
Yes possible |
Possible only in geo tagged data |
C |
13 |
Why Tensorflow uses computational |
Tensors are nothing but computational |
Gaphs are easy to plot |
There is no such concept of computational |
Calculations can be done in parallel |
D |
14 |
How do we perform caculations in |
We launch the computational graph in a |
We launch the sesssion inside a |
By creating multiple tensors |
By creating data frames |
A |
15 |
How do you feed external data into |
by using impoar data command |
by using feed_dict |
by using read data function |
Not possible |
B |
16 |
out=tf.sigmoid(tf.add(tf.matmul(X,W), |
Logistic Regression Equaltion |
Deep ANN equation |
Random Forest Equation |
Linear Regression equation |
A |
17 |
C=-tf.reduce_sum(Y*tf.log(out)) |
C is a logistc regression line equation |
C is a squared error loss function |
C is a cross entropy loss functiom |
C is a linear regression line equation |
C |
18 |
Can we use GPU for faster computations in TensorFlow |
No, not possible |
Possible only on cloud |
Possible only with small datasets |
Yes, possible |
D |
19 |
Which tool is a deep learning wrapper on TensorFlow |
Python |
Keras |
PyTourch |
Azure |
B |
20 |
How deep learning models are built on Keras |
by using sequential models |
by using feed_dict |
by creating place holders and computational |
by creating data frames |
A |
More interview questions in our android app
statinfer app – A new way to learn and test your knowledge on data science
https://play.google.com/store/apps/details?id=com.learn.statinfer1
A fun way of learning data science. App contains interview questions
0 responses on "20 Multiple Choice Questions on TensorFlow"