How sifat192/neural-networks-from-scratch works
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 Tutorial Notebook
Components 14
Neural Network Learning
- Tutorial Notebook
Neural_Networks_From_Scratch.ipynb - Neurons
Neural_Networks_From_Scratch.ipynb - Dense Layer
Neural_Networks_From_Scratch.ipynb - ReLU
Neural_Networks_From_Scratch.ipynb - Softmax
Neural_Networks_From_Scratch.ipynb - Forward Propagation
Neural_Networks_From_Scratch.ipynb - MSE Loss
Neural_Networks_From_Scratch.ipynb - Binary Cross-Entropy
Neural_Networks_From_Scratch.ipynb - Categorical Cross-Entropy
Neural_Networks_From_Scratch.ipynb - Partial Derivatives
Neural_Networks_From_Scratch.ipynb - Backpropagation
Neural_Networks_From_Scratch.ipynb - Gradient Descent
Neural_Networks_From_Scratch.ipynb
Other components
- Learner
- NumPy
Connections 20
- 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