dl-exp3's Introduction

Convolutional Deep Neural Network for Digit Classification

AIM

To Develop a convolutional deep neural network for digit classification and to verify the response for scanned handwritten images.

Problem Statement and Dataset

The MNIST dataset is a collection of handwritten digits. 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. The dataset has a collection of 60,000 handwrittend digits of size 28 X 28. Here we build a convolutional neural network model that is able to classify to it's appropriate numerical value.

Neural Network Model

DESIGN STEPS

STEP 1:

Download and load the dataset

STEP 2:

Scale the dataset between it's min and max values

STEP 3:

Using one hot encode, encode the categorical values

STEP 4:

Split the data into train and test

STEP 5:

Build the convolutional neural network model

STEP 6:

Train the model with the training data

STEP 7:

Plot the performance plot

STEP 8:

Evaluate the model with the testing data

PROGRAM

https://github.com/yoursenpai69/dl-exp3/blob/main/Copy_of_Ex03_minist_classification.ipynb

OUTPUT

Training Loss, Validation Loss Vs Iteration Plot

Classification Report

Confusion Matrix

New Sample Data Prediction

RESULT

Successfully developed a convolutional deep neural network for digit classification and verified the response for scanned handwritten images.

Recommend Projects

yoursenpai69 / dl-exp3 Goto Github PK