OUALITY ASSESSMENT REPORT

22EC2006-DEEP LEARNING
LANGUAGE TRANSLATOR USING DEEP LEARNING ALGORITHM

Submitted by
U. PRANAY ABHISHEK (URK21EC4011)

Date Of Submission :07/11/2023

BACHELOR OF TECHNOLOGY SEMESTER 5

ELECTRONICS AND COMMUNICATION ENGINEERING

SCHOOL OF ENGINEERING AND TECHNOLOGY

KARUNYA INSTITUTE OF TECHNOLOGY AND SCIENCES

(Deemed to be university)
Karunya Nagar, Coimbatore - 641 114. INDIA November 2023
 MNIST HANDWRITTEN NUMBER DETECTION
OBJECTIVE
The MNIST database (Modified National Institute of Standards and
Technology database) is a large database of handwritten digits that is commonly used for
training various image processing systems. The database is also widely used for training
and testing in the field of Deep learning.

THEORY

The model we used is built with Keras using Convolutional Neural Networks (CNN).
A convolutional neural network is a special type of deep neural network which performs
extremely well for image classification purposes. A CNN basically consists of an input
layer, an output layer and a hidden layer which can have multiple layers. A convolution
operation is performed on these layers using a filter that performs 2D matrix
multiplication on the layer and filter.
The CNN model architecture consists of the following layers:

• Convolutional layer; 32 nodes, kernel size 3

• Convolutional layer; 32 nodes, kernel size 3
• Convolutional layer; 64 nodes, kernel size 3
• Fully connected layer; 128 nodes
The final layer is also a fully connected layer with 2 nodes.
Here we are just randomly visualizing our 28X28 images.
It is a dataset of 60,000 small square 28×28 pixel grayscale images of handwritten single
digits between 0 and 9. The task is to classify a given image of a handwritten digit into
one of 10 classes representing integer values from 0 to 9, inclusively.
PROGRAM
OUTPUT :

CONCLUSION :

Here, a popular dataset called MNIST was taken to make the classification of
handwritten digits from 0 to 9. The dataset was cleaned, scaled, and shaped. Using
Keras, a CNN model was created and trained on the training dataset.