public Sequential(layers as IList<Layer<T>>)
Snapshots the order of a non-empty list of layers without copying parameters. Reusing one layer in multiple positions is rejected: shared-weight graphs require summed parameter gradients, not separate optimizer steps.
| Parameter | Description |
|---|---|
layers | Distinct, non-null stages in forward order. |
model = Sequential<Float>([Dense<Float>(128), ReLU<Float>(), Dense<Float>(10)])