Scribd
Upload
14 views2 pages

AI - Module 1&2

The document outlines an assignment for a course on Artificial Intelligence, focusing on Deep Learning applications. It includes tasks such as defining a use case, automating inspection processes in steel manufacturing, creating models using numpy, and explaining concepts like Learning Rate and activation functions. Additionally, it requires mathematical derivations and practical implementations related to Deep Learning projects.

Uploaded by

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

AI - Module 1&2

The document outlines an assignment for a course on Artificial Intelligence, focusing on Deep Learning applications. It includes tasks such as defining a use case, automating inspection processes in steel manufacturing, creating models using numpy, and explaining concepts like Learning Rate and activation functions. Additionally, it requires mathematical derivations and practical implementations related to Deep Learning projects.

Uploaded by

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

Artificial Intelligence

Module 1 and 2 Assignment

support@intellipaat.com

+91-7022374614

US: 1-800-216-8930 (Toll-Free)


Assignment Questions

Tasks to be performed:
1. Define a use case of Deep Learning in your current domain (if fresher, pick
any of your favorite) and propose a solution through DL.
2. A steel manufacturing plant is spending many hours in manual inspection
of their steel product(flat 2*2 ft steel plates) The inspection is a crucial part
of their delivery cycle.
a. Design and detail out a proposal to automate the process using DL
b. Please, explain what will be your major questions to client regarding
the process & data
3. A particular linear process has an input (x=5) and output (y=10)
a. Create a model using numpy to solve for “y” and record your best
error.
b. Repeat the above experiment with different hyper parameters like
Learning Rate & activation function.
c. Record the various hyperparameters used in experiment and submit
the table with data (x | y | y_pred | error (RMSE) | LR | activation
used).
4. Define the role of Learning Rate in Neural Networks and why they are
important using an experiment?
a. Use an experiment like above one with LR and one without LR.
5. Explain the 3 step life cycle of Deep Learning projects with an example use
case.
6. Mathematically, derive the complete process of a single perceptron from
an input to output and perform the below task:
a. Explain the above in 3 phases of Feed Forward, Error Calculation,
Back Propagation mathematically.
b. Explain the role and importance of each and every parameter other
than x and y.
7. What are activation functions and why are they required in NN?
a. Create python functions for sigmoid, tanh, relu & softmax.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy