metadata
license: apache-2.0
Implemented as a Multi-Layer Perceptron to classify handwritten Digits (0-9)
Model Architecture and Results
The model comprises a flattening layer and three linear layers ((128, 64) hidden dimensions) with relus to approximate non-linearity. It achieves 90% accuracy after 10 training epochs and batch size = 128. Taining and Test MNIST datasets are loaded with PyTorch dataloaders.