cpu_version/networks/s_network library

Classes

SNetwork

A sequential neural network architecture that linearly stacks and executes Layer instances. Manages sequential forward propagation, parameter aggregation across constituent layers, training loops via fit, weight serialization to JSON via save and load, and autograd graph visualization.

Functions

main() → Future<void>

Demonstrates training, saving, loading, and evaluating an SNetwork model on the XOR problem.