Backpropagation in Neural Networks

[SnehaGupta0206]

Pull Request for DL-Simplified 💡

Issue Title: Backpropagation in Neural Networks

• Info about the related issue (Aim of the project): To demonstrate the implementation of Backpropagation in Neural Networks and compare different optimization techniques including Gradient Descent, Stochastic Gradient Descent (SGD), Mini-Batch Gradient Descent and Adam Optimizer using the Iris Dataset.
• Name: Sneha Gupta
• GitHub ID: SnehaGupta0206
• Email ID: 02snehagupta06@gmail.com
• Identify yourself: GSSOC 2026 Participant

Closes: #issue 885

Describe the add-ons or changes you've made

• Performed Exploratory Data Analysis (EDA) on the Iris Dataset.
• Generated visualizations including:
  • Class Distribution
  • Correlation Heatmap
  • Pairplot
• Applied Data Preprocessing:
  • Label Encoding
  • Feature Scaling
  • Train-Test Split
• Implemented Neural Network using Backpropagation.
• Compared the following optimization techniques:
  • Gradient Descent (GD)
  • Stochastic Gradient Descent (SGD)
  • Mini-Batch Gradient Descent
  • Adam Optimizer
• Evaluated models using:
  • Accuracy Comparison
  • Loss Comparison
  • Confusion Matrix
  • Classification Report
• Added project documentation and requirements file.
  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?

• Executed the notebook successfully in Jupyter Notebook.
• Verified preprocessing, training, and evaluation steps.
• Compared model performance using accuracy and loss metrics.
• Validated results using confusion matrix and classification report.

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]

Our team will soon review your PR. Thanks @SnehaGupta0206 :)