Four-Layer Neural Network from Scratch (NumPy)

A fully-connected network built with only NumPy: hand-derived backpropagation and mini-batch SGD, no deep-learning framework. It reaches 97.83% test accuracy on MNIST and trains in about 88 seconds on a Colab CPU.

Model Details

  • Author: Vishwajeet Adkine
  • Architecture: 784 β†’ 128 β†’ 64 β†’ 32 β†’ 10 (four weight layers, 111,146 parameters)
  • Activations / loss: ReLU hidden layers, softmax output, cross-entropy with optional L2
  • Initialisation: He (normal, variance 2 / fan-in)
  • Implementation: NumPy NeuralNetwork class with forward, backward, step and fit; backprop verified against numerical gradients before training

Intended Use

Learning and demonstration: seeing exactly how forward propagation, backpropagation and SGD work, without framework abstractions. Not intended for production use.

Training

Data MNIST (90% train / 10% validation split of the training set, official test set held out)
Preprocessing pixels scaled to [0, 1], flattened to 784
Optimiser mini-batch SGD, batch size 128
Learning rate 0.1 with Γ—0.95 decay per epoch
Regularisation L2, Ξ» = 1e-4
Epochs 30 (default notebook config)
Hardware Colab CPU

Results

Metric Value
Test accuracy 97.83%
Test loss 0.0824
Training time 88.2 s (Colab CPU)

Limitations

  • Fully-connected layers ignore image structure, so accuracy is below convolutional models (the CIFAR-10 CNN project in this series covers that step).
  • Plain SGD with a fixed decay: no momentum, Adam, dropout or batch normalisation.
  • Evaluated on MNIST only, which is an easy, clean benchmark. Do not expect this accuracy on other digit images (different handwriting, backgrounds or scanning).
  • No robustness or calibration analysis.

How to Use

net = load_weights("nn_weights.npz")     # helper defined in the notebook
pred = net.predict(X_test[:5])

Licence

Code and weights: MIT. MNIST is by LeCun, Cortes and Burges.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Dataset used to train vishwajeet456/NumPy