MNIST Digit Classification using Neural Networks

[brahmamyv]

Deep Learning Simplified Repository (Proposing new issue)

🔴 Project Title : MNIST Digit Classification using Neural Networks

🔴 Aim : MNIST is a widely used dataset of handwritten digits that contains 60,000 handwritten digits for training a deep learning model and 10,000 handwritten digits for testing the model

🔴 Dataset :https://www.kaggle.com/c/digit-recognizer

🔴 Approach : MNIST Classification comes under the Image Classification domain , by using Neural network.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

🔴🟡 Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

✅ To be Mentioned while taking the issue :

• Full name : Venkata Brahmam Y
• GitHub Profile Link : https://github.com/brahmamyv
• Email ID : venyb25@gmail.com
• Participant ID (if applicable):
• Approach for this Project :: I will perform Deep Neural network techniques to do this project by tensorflow and PIL from image classification.
• What is your participant role? (Mention the Open Source program)
  Social Summer Of Code '23

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[abhisheks008]

What are the deep learning methods you are planning to implement here for this project?
@brahmamyv

[brahmamyv]

Neural network(NN), by setting up 1 flatten and 3 dense layers.

[abhisheks008]

Try to implement at least 3 methods for this dataset, and find out the best fitted model depending upon the accuracy and loss score of them.

Issue assigned to you @brahmamyv. All the best!

[Im-Shivaprakash]

Full name : Shivaprakash S
GitHub Profile Link : https://github.com/Im-Shivaprakash
Email ID :shivaprakashsrinivasaniam@gmail.com
Participant ID (if applicable):
Approach for this Project :I'll be using feed forwrad network and cnn in this project
What is your participant role? I dont understand this question, Im new to open source project platform

[raniasyed]

Full name : Rania
GitHub Profile Link :https://github.com/raniasyed
Email ID : syedraniaxxx@gmail.com
Participant ID (if applicable):
Approach for this Project : I will be making use of the CNN model since it is the best fit for the dataset used in the project.
What is your participant role? CollabCode-Carnival

[abhisheks008]

Hi @raniasyed thank you for showing interest in Deep Learning Simplified project repository. Try to use 2-3 deep learning methods for solving this project and compare the models to find out the best fitted one.

Issue assigned to you. Go ahead!

[abhisheks008]

This issue will not be considered under CollabCode Open Source event organized by OSEN as the program ends on November 20th, 2023.

[Cgarg9]

Full name : Chirag Garg
GitHub Profile Link : https://github.com/Cgarg9
Email ID : chiraggarg.red@gmail.com
Participant ID (if applicable):
Approach for this Project :: I would first apply simple artificial neural networks. Then I would solve this issue using CNN. at last I would try to use ResNet model.
What is your participant role? (Mention the Open Source program)
Codepeak23

[abhisheks008]

Issue assigned to you @Cgarg9