KEMBAR78
Data Science Internship | PDF
Scribd
Upload
50 views2 pages

Data Science Internship

The document advertises a data science internship. It notes that the applicant's name and photo from their Google account will be recorded when files are uploaded or the form is submitted. It also states that any uploaded files will be shared outside the organization. At the bottom, it provides a link to switch Google accounts if the current one is not the applicant's.

Uploaded by

amit kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
50 views2 pages

Data Science Internship

The document advertises a data science internship. It notes that the applicant's name and photo from their Google account will be recorded when files are uploaded or the form is submitted. It also states that any uploaded files will be shared outside the organization. At the bottom, it provides a link to switch Google accounts if the current one is not the applicant's.

Uploaded by

amit kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Data Science Internship

The name and photo associated with your Google account will be recorded when you upload
files and submit this form.

Any files that are uploaded will be shared outside of the organization they belong to.

Not imt_2017009@iiitm.ac.in? Switch account

* Required

Test

Why and when to choose CNN over Feed Forward neural network? *

Convolutional neural network is better than a feed-forward network since CNN has features
parameter sharing and dimensionality reduction. Because of parameter sharing in CNN, the
number of parameters is reduced thus the computations also decreased.

What are the assumptions made while designing a Neural Network? *

We have a separate layer for both input and output. We use non linear function as activation.

Why do we need non-linear activation layers? *

They allow the model to create complex mappings between the network's inputs and
outputs, which are essential for learning and modeling complex data, such as images, video,
audio, and data sets which are non-linear or have high dimensionality.

Difference between PyTorch and TensorFlow? *

TensorFlow provides a way of implementing dynamic graph using a library called


TensorFlow Fold, but PyTorch has it inbuilt. TensorFlow has faster compile times than
PyTorch and provides flexibility for building real-world applications.
What is Weight Initialization Strategy for deep learning? *

Random initialization can cause Vanishing gradient problem. That's why there are some
other initialization method that were introduced RandomNormal class , RandomUniform
class , TruncatedNormal class , Zeros class.

How ResNet Works? *

ResNet stands for Residual Network it is used for CNNs for Image Classification Tasks. It
has skip connections to deal the problem of vanishing gradient

Back Submit

Never submit passwords through Google Forms.

This form was created inside of ArabEasy. Report Abuse

 Forms

You might also like