FAIRFIELD INSTITUTE OF MANAGEMENT AND TECHNOLOGY
DEEP LEARNING WITH PYTHON
PRACTICAL FILE
SUBJECT CODE – BCA(314)
SUBMITTED TO: - SUBMITTED BY: -
Mr. Shashikant Tiwari Nishant Kumar
Asst.Professor (B.C.A 6th Sem)
I.T Department Enrollment No.- 00190102022
INDEX
S. No. Practicals Page No. Sign
Write a program for creating a perceptron.
1) 03
2) 04
Write a program to implement multi-layer perceptron using TensorFlow.
Apply multi-layer perceptron (MLP) on the Iris dataset.
3) (a) Write a program to implement a Convolution Neural Network 05
(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.
4) (a) Write a program to perform face detection using CNN. 09
(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.
5) Write a program to build auto-encoder in Keras. 17
6) Write a program to implement basic reinforcement learning algorithm to 19
teach a bot to reach its destination.
(a) Write a program to implement a Recurrent Neural Network
7) (b) Write a program to implement LSTM and perform time series 22
analysis using LSTM.
8) (a) Write a program to perform object detection using Deep Learning (b) 26
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.
(a) Write a program to demonstrate different activation functions.
9) (b) Write a program in TensorFlow to demonstrate different Loss 30
functions.
10) Write a program to build an Artificial Neural Network by implementing 34
the Back propagation algorithm and test the same using appropriate data
sets
Q1. Write a program for creating a perceptron.
Code:
#output:
Q2. Write a program to implement multi-layer perceptron using TensorFlow. Apply multi-
layer perceptron (MLP) on the Iris dataset.
Code:
#output:
Q3.
(a) Write a program to implement a Convolution Neural 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.
Code:
# (a) CNN implementation and prediction
#output:
Code:
# (b) CIFAR-10 Image Classifier
#output:
Q4. (a) Write a program to perform face detection using CNN.
(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.
Code:
# a) face detection using CNN
#output:
# b) Hyperparameter tuning in CNN Code:
#output
Code:
# c) Bike sharing patterns
#output:
Q5. Write a program to build auto-encoder in Keras Code:
#output:
Q6. Write a program to implement basic reinforcement learning algorithm to teach a bot to
reach its destination.
Code:
#output:
Q7. (a) Write a program to implement a Recurrent Neural Network
(b) Write a program to implement LSTM and perform time series analysis using LSTM.
Code:
# a)Simple RNN
#output:
Code:
# b)Write a program to implement LSTM and perform time series analysis using LSTM.
#output:
Q8. (a) Write a program to perform object detection using Deep 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.
Code:
Code:
# b) Dog breed classifier
#output:
Q9. (a) Write a program to demonstrate different activation functions.
(b) Write a program in TensorFlow to demonstrate different Loss functions.
Code:
# (a) Write a program to demonstrate different activation functions.
#output:
Code:
# b) Demonstrate Different Loss Functions in TensorFlow
#output:
Q10. Write a program to build an Artificial Neural Network by implementing the Back
propagation algorithm and test the same using appropriate data sets.
Code:
#output:
