https://github.com/hchandeepa/neural_network_for_handwritten_digits_classification

This is a neural network for hand written numerics.
https://github.com/hchandeepa/neural_network_for_handwritten_digits_classification

jupyter-notebook neural-network python

Last synced: 5 days ago
JSON representation

This is a neural network for hand written numerics.

• Host: GitHub
• URL: https://github.com/hchandeepa/neural_network_for_handwritten_digits_classification
• Owner: HChandeepa
• Created: 2024-07-25T17:31:05.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-08-11T17:27:37.000Z (3 months ago)
• Last Synced: 2024-09-13T16:19:33.263Z (2 months ago)
• Topics: jupyter-notebook, neural-network, python
• Language: Jupyter Notebook
• Homepage:
• Size: 191 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Handwritten Digits Classification using Neural Networks

In this project, I build a neural network from scratch using TensorFlow and Python to classify handwritten digits. The project progresses from a simple model to a more complex architecture, allowing us to observe the impact of additional layers on model performance.

## Project Overview

### Initial Model:

We begin by building a basic neural network with only an input layer and an output layer. This model serves as a baseline for comparison.

Model Enhancement:

After evaluating the performance of the initial model, we add a hidden layer to the network. This allows us to analyze how the model's performance improves with the addition of more layers and complexity.

### Dataset

We use the popular MNIST dataset, which consists of 28x28 pixel images of handwritten digits (0-9). The dataset is readily available in TensorFlow and is commonly used for benchmarking classification algorithms.