brainmass.diffusive_coupling

brainmass.diffusive_coupling(delayed_x, y, conn, k)

Diffusive coupling kernel (function form).

Computes, for each target unit i over the last axis, the diffusive term

current_i = k * sum_j conn[i, j] * (x_{i, j} - y_i)

with full support for leading batch/time dimensions and unit-safe algebra.

Parameters:

• delayed_x (Callable | Array | ndarray | bool | number | bool | int | float | complex | Quantity) – Zero-arg callable returning the source signal with shape (..., N_out, N_in) or flattened (..., N_out*N_in). Typically a Prefetch that reads a state from another module.

• y (Callable | Array | ndarray | bool | number | bool | int | float | complex | Quantity) – Zero-arg callable returning the target signal with shape (..., N_out).

• conn (Array | ndarray | bool | number | bool | int | float | complex | Quantity) – Connection weights. Either (N_out, N_in) or flattened (N_out*N_in,).

• k (Array | ndarray | bool | number | bool | int | float | complex | Quantity) – Global coupling strength. Can be scalar or broadcastable to the output shape (..., N_out).

Returns:

Coupling output with shape (..., N_out). If inputs carry units, the result preserves unit consistency via brainunit.

Return type:

ArrayLike

Raises:

ValueError – If shapes are incompatible with the expected conventions.