Neural Network
March 25, 2026 · View on GitHub
Components for building, training, and evaluating feed-forward neural networks entirely on-device with static memory allocation.
Components
| Component | Description |
|---|---|
| Neural Network Overview | Architecture, training loop, and how the components fit together |
| Layers | Dense (fully connected) layer with forward and backward pass |
| Activation Functions | Non-linear element-wise transforms: ReLU, LeakyReLU, Sigmoid, Tanh, Softmax |
| Loss Functions | Objective functions: MSE, MAE, Binary Cross-Entropy, Categorical Cross-Entropy |
| Model | Variadic-template model composing layers, optimizer, and loss into a trainable pipeline |
See also: Optimization for optimizers (Gradient Descent) and Regularization for weight penalties (L1, L2) — these are general-purpose domains used by neural networks and other algorithms.