Added MNIST classification using MLP (only numPy)

[ayushi2626]

Pull Request for PyVerse 💡

Issue Title :

• Info about the related issue (Aim of the project) : The goal of the project is to develop a MLP or Multi-Layered Perceptron to classify digits of MNIST dataset
• Name: Ayushi Bhargav
• GitHub ID: https://github.com/ayushi2626
• Email ID: ayushibhargav2002@gmail.com
• Idenitfy yourself: (Mention in which program you are contributing in. Eg. For a WoB 2024 participant it's, WoB Participant) GSSOC 2024

Closes: #issue number that will be closed through this PR
#18

Describe the add-ons or changes you've made 📃

I have created a model of MLP to classify MNIST dataset. The model uses just numPy and uses mathematical implementations of forward and backward passes to train the same. The accuracy is 97 percent on test data.

Type of change ☑️

What sort of change have you made:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Code style update (formatting, local variables)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested? ⚙️

The model is tested in MNISt dataset.

Checklist: ☑️

• My code follows the guidelines of this project.
• I have performed a self-review of my own code.
• I have commented my code, particularly wherever it was hard to understand.
• I have made corresponding changes to the documentation.
• My changes generate no new warnings.
• I have added things that prove my fix is effective or that my feature works.
• Any dependent changes have been merged and published in downstream modules.

[github-actions]

👋 Thank you for opening this pull request! We're excited to review your contribution. Please give us a moment, and we'll get back to you shortly!

[UTSAVS26]

Please add detailed documentation in this format.

[ayushi2626]

Hey should I add documentation in the code or in the issue template?

[UTSAVS26]

Hey should I add documentation in the code or in the issue template?

You need to create a new readme file for the project and the template for he readme file is attached above for reference.

[UTSAVS26]

@ayushi2626 what's the update?

[ayushi2626]

@ayushi2626 what's the update?

Hey, I will be updating it by tonight. So sorry for the delay something urgent had popped up.

[TheChaoticor]

@ayushi2626 what's the update?

Hey, I will be updating it by tonight. So sorry for the delay something urgent had popped up.

No problem.we just wanted to make sure if you are actively solving the issue

[TheChaoticor]

Please add some use cases of classifications,only printing the accuracy is not viable for a pull request.But i admire the cleanliness of your code.Just add some examples

[ayushi2626]

Please add some use cases of classifications,only printing the accuracy is not viable for a pull request.But i admire the cleanliness of your code.Just add some examples

Sure I will add other performance metrics along with the accuracy for better visualization. Thank you very much!

[ayushi2626]

Hey I am working on the readme file and trying to improve the readability of the code and fixing a few minor details in the same. I will finish both of these and get back to you guys at the earliest. Thank you very much!

[UTSAVS26]

Hey I am working on the readme file and trying to improve the readability of the code and fixing a few minor details in the same. I will finish both of these and get back to you guys at the earliest. Thank you very much!

Any updates?

[UTSAVS26]

@ayushi2626 I am closing this PR by the EOD.

[Sai-ganesh-0004]

Hello I would like to work on it Can I have a chance

[UTSAVS26]

Hello I would like to work on it Can I have a chance

You can raise a new issue and when i assign it you you can work on the PR as i am closing this PR as already this PR has been active for so long and no response is there.

[ayushi2626]

Hey I am extremely sorry my laptop was not working and I do not have my github login on my phone. So I wasn't able to convey any progress here. I have coded the MLP but used the wrong dataset by mistake and I was trying to fix it to fit the MNIST dataset. If possible I can still try and finish the work although it can be time-consuming as the data is a little difficult to fit.

[ayushi2626]

I can open a new PR for the iris dataset if possible as it shows very good accuracy with it. Anyway so sorry for all the needless trouble you had to take.