0% found this document useful (0 votes)
6 views40 pages

DL Assignment

The document is a lab file for the Deep Learning Lab course at Noida Institute of Engineering and Technology for the session 2024-2025. It includes various exercises such as dataset splitting, binary classification of fruits, predicting exam scores using linear regression, visualizing activation functions, and implementing convolutional neural networks. The lab work is submitted by a student named Piyush to Dr. Raju, an Associate Professor in AIML.

Uploaded by

piyushjaat112
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
0% found this document useful (0 votes)
6 views40 pages

DL Assignment

The document is a lab file for the Deep Learning Lab course at Noida Institute of Engineering and Technology for the session 2024-2025. It includes various exercises such as dataset splitting, binary classification of fruits, predicting exam scores using linear regression, visualizing activation functions, and implementing convolutional neural networks. The lab work is submitted by a student named Piyush to Dr. Raju, an Associate Professor in AIML.

Uploaded by

piyushjaat112
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

CSE-AIML Deep Learning Lab

NOIDA INSTITUTE OF ENGINEERING AND


TECHNOLOGY GREATER NOIDA-201306
(An Autonomous Institute)
School of Computer Sciences & Engineering in Emerging
Technologies

Department of CSE-Artificial Intelligence


and Machine Learning

Session (2024 – 2025)

LAB FILE
on

Deep Learning Lab


(ACSML0652)
(6th Semester)

Submitted By: Submitted To:

Name: Piyush Name: Dr. Raju


Roll No.: 2201331530144 (Associate Professor, AIML)

Affiliated to Dr. A.P.J Abdul Kalam Technical University, Uttar Pradesh, Lucknow
CSE-AIML Deep Learning Lab

S. No.
Date TITLE Pg No.

1. Split any dataset into training and testing data.

2. Classify fruits as either apple or banana based on their diameter


(in cm) and weight (in grams) using a binary classification
model.
3. Predict the exam score of a student based on the number of
study hours using a linear regression model. Given a dataset of
study hours and corresponding exam scores, the goal is to train
a model and make predictions for a specified number of study
hours.
4. Visualize the behavior of different activation functions (sigmoid, softmax,
ReLU, leaky ReLU, ELU, and tanh). Compare their outputs by plotting
how each activation function transforms input values.
5. Create a program that allows the user to select a logical gate
(AND, OR, XOR, NAND, or NOR), input values for three
variables (x1, x2, x3), and calculate the result using the s
selected gate's activation function. The program should display
the result based on the weighted sum of the inputs and the
chosen gate.
6. Classify the model's predictions into "Churn" or "Stay" based
on a threshold of 0.5. If the predicted probability is greater than 0.5, label
the result as "Churn"; otherwise, label it as "Stay."
7. Implement the Convolution neural network with padding and Striding.
8. Apply different types of padding over an image and visualize their effect.
9. Add the two image pixel-wise and visualize the result.

INDEX
CSE-AIML Deep Learning Lab
1. Split any dataset into training and testing data.
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab

2. Classify fruits as either apple or banana based on their diameter


(in cm) and weight (in grams) using a binary classification model.
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab

3. Predict the exam score of a student based on the number of study


hours using a linear regression model. Given a dataset of study
hours and corresponding exam scores, the goal is to train a model
and make predictions for a specified number of study hours.
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab

4. Visualize the behavior of different activation functions (sigmoid,


softmax, ReLU, leaky ReLU, ELU, and tanh). Compare their outputs
by plotting how each activation function transforms input values.
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab

5. Create a program that allows the user to select a logical gate (AND,
OR, XOR, NAND, or NOR), input values for three variables (x1, x2,
x3), and calculate the result using the selected gate's activation
function. The program should display the result based on the
weighted sum of the inputs and the chosen gate.
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
6. Classify the model's predictions into "Churn" or "Stay" based on a
threshold of 0.5. If the predicted probability is greater than 0.5, label
the result as "Churn"; otherwise, label it as "Stay."
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
7. Implement the Convolution neural network with padding and
Striding.
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
8. Apply different types of padding over an image and visualize their
effect.
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab
9. Add the two images pixel-wise and visualize their effect.
CSE-AIML Deep Learning Lab
CSE-AIML Deep Learning Lab

You might also like