# sifat192/neural-networks-from-scratch architecture

> Architecture diagram of the GitHub repository sifat192/neural-networks-from-scratch, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-28). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sifat192/neural-networks-from-scratch
- Repository: https://github.com/sifat192/neural-networks-from-scratch

## Overview

This is a small educational project centered on one Jupyter notebook: it implements neural-network fundamentals with Python and NumPy. The README documents a conceptual progression from layers and activations through losses, backpropagation, and gradient descent. The notebook source was not sampled, so the graph reflects documented topics rather than asserting unverified implementation details.

Main entry points: [`Neural_Networks_From_Scratch.ipynb`](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb) (Tutorial Notebook)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_learning["Neural Network Learning"]
  node_notebook["Tutorial Notebook"]
  node_neuron["Neurons"]
  node_dense["Dense Layer"]
  node_relu["ReLU"]
  node_softmax["Softmax"]
  node_forward["Forward Propagation"]
  node_mse["MSE Loss"]
  node_bce["Binary Cross-Entropy"]
  node_categorical["Categorical Cross-Entropy"]
  node_derivatives["Partial Derivatives"]
  node_backprop["Backpropagation"]
  node_gradient["Gradient Descent"]
end

node_learner(("Learner"))
node_numpy["NumPy"]

node_learner -->|"works through"| node_notebook
node_notebook -->|"implements"| node_neuron
node_notebook -->|"implements"| node_dense
node_notebook -->|"implements"| node_relu
node_notebook -->|"implements"| node_softmax
node_notebook -->|"covers"| node_forward
node_notebook -->|"implements"| node_mse
node_notebook -->|"implements"| node_bce
node_notebook -->|"implements"| node_categorical
node_notebook -->|"covers"| node_derivatives
node_notebook -->|"implements"| node_backprop
node_notebook -->|"implements"| node_gradient
node_notebook -->|"uses"| node_numpy
node_neuron -->|"builds"| node_dense
node_dense -->|"supports"| node_forward
node_forward -->|"feeds"| node_mse
node_forward -->|"feeds"| node_bce
node_forward -->|"feeds"| node_categorical
node_derivatives -->|"supports"| node_backprop
node_backprop -->|"supports"| node_gradient

click node_notebook "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_neuron "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_dense "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_relu "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_softmax "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_forward "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_mse "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_bce "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_categorical "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_derivatives "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_backprop "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"
click node_gradient "https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_notebook,node_neuron,node_dense,node_relu,node_softmax,node_forward,node_mse,node_bce,node_categorical,node_derivatives,node_backprop,node_gradient toneBlue
class node_learner,node_numpy toneIndigo
```

## Components

### Neural Network Learning

- [Tutorial Notebook](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [Neurons](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [Dense Layer](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [ReLU](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [Softmax](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [Forward Propagation](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [MSE Loss](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [Binary Cross-Entropy](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [Categorical Cross-Entropy](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [Partial Derivatives](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [Backpropagation](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`
- [Gradient Descent](https://github.com/sifat192/neural-networks-from-scratch/blob/main/Neural_Networks_From_Scratch.ipynb): `Neural_Networks_From_Scratch.ipynb`

### Other components

- **Learner**
- **NumPy**

## Connections

- Learner → Tutorial Notebook: works through
- Tutorial Notebook → Neurons: implements
- Tutorial Notebook → Dense Layer: implements
- Tutorial Notebook → ReLU: implements
- Tutorial Notebook → Softmax: implements
- Tutorial Notebook → Forward Propagation: covers
- Tutorial Notebook → MSE Loss: implements
- Tutorial Notebook → Binary Cross-Entropy: implements
- Tutorial Notebook → Categorical Cross-Entropy: implements
- Tutorial Notebook → Partial Derivatives: covers
- Tutorial Notebook → Backpropagation: implements
- Tutorial Notebook → Gradient Descent: implements
- Tutorial Notebook → NumPy: uses
- Neurons → Dense Layer: builds
- Dense Layer → Forward Propagation: supports
- Forward Propagation → MSE Loss: feeds
- Forward Propagation → Binary Cross-Entropy: feeds
- Forward Propagation → Categorical Cross-Entropy: feeds
- Partial Derivatives → Backpropagation: supports
- Backpropagation → Gradient Descent: supports