VIVEKANANDA INSTITUTE OF PROFESSIONAL STUDIES
VIVEKANANDA SCHOOL OF INFORMATION
TECHNOLOGY
BACHELOR OF COMPUTER APPLICATION
PRACTICAL-XII
DEEP LEARNING USING PYTHON LAB
BCAP 314
Guru Gobind Singh Indraprastha University Sector - 16C,
Dwarka, Delhi – 110078
SUBMITTED TO: SUBMITTED BY:
Ms. Tanvi Dalal Plaksha Gupta
Assistant Professor 01129802023
VIPS BCA- 6 EA
INDEX
[Link]. TITLE DATE SIGNATURE
1 Write a program to implement single layer perceptron for AND, 19.02.2026
OR and NOT logic gates and analyse results.
2 Write a program to demonstrate the limitations of single layer 19.02.2026
perceptron by implementing XOR logic gate.
3 Write a program for creating a perceptron. (Implement MLP for 26.02.2026
XOR problem).
4 Write a program to implement multi-layer perceptron using Tensor 26.02.2026
Flow. Apply multi-layer perceptron (MLP) on the Iris dataset.
5 (a) Write a program to implement a Convolution Neural 05.03.2026
Network (CNN) in Keras. Perform predictions using the
trained Convolution Neural Network (CNN).
(b) Write a program to build an Image Classifier with CIFAR-
10 Data.
6 (a) Write a program to perform face detection using CNN. 05.03.2026
(b) Write a program to demonstrate hyperparameter tuning in
CNN.
(c) Predicting Bike-Sharing Patterns – Build and train neural
networks from scratch to predict the number of bike share
users on a given day.
7 Write a program to perform data augmentation with hep of Python 12.03.2026
and Keras.
8 Write a program to build auto-encoder in Keras. 12.03.2026
9 Write a program to implement basic reinforcement learning 19.03.2026
algorithm to teach a bot to reach its destination.
10 (a) Write a program to implement a Recurrent Neural Network 19.03.2026
(b) Write a program to implement LSTM and perform time
series analysis using LSTM.
11 (a) Write a program to perform object detection using Deep 02.04.2026
Learning
(b) Dog-Breed Classifier – Design and train a convolutional neural
network to analyze images of dogs and correctly identify their
breeds. Use transfer learning and well-known architectures to
improve this model.
12 (a) Write a program to demonstrate different activation functions. 09.04.2026
(b) Write a program in TensorFlow to demonstrate different Loss
functions.
13 Write a program to build an Artificial Neural Network by 10.04.2026
implementing the Back propagation algorithm and test the same
using appropriate data sets
14 Synopsis and implementation of research paper selected 10.04.2026
Q1. Write a program to implement single layer perceptron for AND, OR and
NOT logic gates and analyse results.
SOURCE CODE
OUTPUT
Q2. Write a program to demonstrate the limitations of single layer
perceptron by implementing XOR logic gate.
SOURCE CODE:
OUTPUT:
Q3. Write a program for creating a perceptron. (Implement MLP for XOR
problem).
SOURCE CODE:
OUTPUT:
Q4. Write a program to implement multi-layer perceptron using Tensor
Flow. Apply multi-layer perceptron (MLP) on the Iris dataset.
SOURCE CODE:
OUTPUT:
Q5. (a) Write a program to implement a Convolution Neural Network (CNN)
in Keras. Perform predictions using the trained Convolution Neural
Network (CNN).
SOURCE CODE:
OUTPUT:
Q5 (b) Write a program to build an Image Classifier with CIFAR-10 Data.
SOURCE CODE
OUTPUT
Q6. (a) Write a program to perform face detection using CNN.
SOURCE CODE:
OUTPUT:
Q6 (b) Write a program to demonstrate hyperparameter tuning in CNN.
SOURCE CODE
OUTPUT
Q6 (c) Predicting Bike-Sharing Patterns – Build and train neural networks from
scratch to predict the number of bike share users on a given day.
SOURCE CODE:
OUTPUT:
Q7. Write a program to perform data augmentation with help of Python and
Keras.
SOURCE CODE
OUTPUT
Q8. Write a program to build auto-encoder in Keras.
SOURCE CODE:
OUTPUT:
Q9. Write a program to implement basic reinforcement learning algorithm to
teach a bot to reach its destination.
SOURCE CODE:
OUTPUT:
Q10 (a) Write a program to implement a Recurrent Neural Network
SOURCE CODE:
OUTPUT:
Q10 (b) Write a program to implement LSTM and perform time series analysis using
LSTM
SOURCE CODE
OUTPUT
Q11 (a) Write a program to perform object detection using Deep Learning
SOURCE CODE:
OUTPUT
Q11 (b) Dog-Breed Classifier – Design and train a convolutional neural network to
analyze images of dogs and correctly identify their breeds. Use transfer learning
and well-known architectures to improve this model
SOURCE CODE
OUTPUT:
Q12 (a) Write a program to demonstrate different activation functions
SOURCE CODE:
OUTPUT:
Q12 (b) Write a program in TensorFlow to demonstrate different Loss functions.
SOURCE CODE:
OUTPUT:
Q13 Write a program to build an Artificial Neural Network by implementing the Back
propagation algorithm and test the same using appropriate data sets
SOURCE CODE:
OUTPUT: