Understanding_and_Creating_NNs

Nothing But NumPy: Understanding & Creating Neural Networks with Computational Graphs from Scratch

This repository is part of the blog post "Nothing but NumPy: Understanding & Creating Neural Networks with Computational Graphs from Scratch"

Forks rather than Clones, Stars rather than Views 🙏

Layers

The Layers directory contains the classes for:

1. Linear Layer
2. Activation Layer:
   • Sigmoid Layer

util

util directory contains utility fuctions. It has the following files with the following functions:

1. paramInitializer.py

   • initialize_parameters(n_in, n_out, ini_type='plain')

2. utilities.py

   • compute_cost(Y, Y_hat)
   • predict(X, Y, Zs, As)
   • plot_learning_curve(costs, learning_rate, total_epochs, save=False)
   • predict_dec(Zs, As, X)
   • plot_decision_boundary(model, X, Y, feat_crosses=None, save=False)
   • plot_decision_boundary_shaded(model, X, Y, feat_crosses=None, save=False)

---

As examples following neural network architectures have been implemented:

1. A 2-layer neural network on XOR data

2. A 1-layer neural network with a feature cross on XOR data

3. A 3-layer neural network on XOR data

---

Find me on twitter for any questions or suggestions.