Gaussian Projection Process

Description:

Connects N-dimensional sheets with equal numbers of dimensions to each other. Connection fields are gaussian with sigma values along each dimension, or globally specified. Learning is implemented. If learning, decimation or inversion are not required, and the sheets are 2D, consider the faster gaussianIIR implementation.

State data:

sigma (DOUBLE) Nx1/1x1:

Either a single global sigma value for all dimensions, or an N number array with specific sigma values for each of the N dimensions. A sigma of 0 along a dimension defaults to a onetoone connection along that dimension.

cacheNum (DOUBLE) 1x1:

A value that can be used to uniquely identify a projection's cache, required when using multiple learning projections with identical starting parameters.

offset (DOUBLE) Nx1:

A list of N offsets given in Locs along each of the N dimensions. Shifts the projection pattern centre on the destination sheet.

delay (DOUBLE) 1x1 (default = 0):

Number of simulation time seconds that data will be delayed before being passed on. If delay is not an exact number of simulation iterations a warning will be generated.

invert (UINT32) 1x1 (default = 0):

Invert the connection pattern. (does nothing).

decimate (DOUBLE) 1x1 (default = 0):

Amount of weights to randomly cull (0->1, 0 = none, 1 = all).

norm (STRING) ('none'; 'aff'; 'affx'; 'eff'; 'effx'; 'proj') (default = 'affx'):

The normalisation type. 'none' is no normalisation, 'aff' is normalisation over afferent connections, with 'affx' using the MAXIMUM normalisation value for all connections (to eliminate edge effects), 'eff' is normalisation over efferent connections, with 'effx' using the MAXIMUM normalisation value for all connections (to eliminate edge effects), 'proj' normalises over projections (efferents AND afferents).

learningRule (STRING) ('???'):

A string giving the BRAHMS namespace path of any valid ModLIN learning utility. See the Learning section for the parameters that can be passed to the learning utility through a learning projection.