glim¶
A Layer that inverts a glm Layer with the same Variables. Inputs an Adjacency matrix and a Feature vector, and returns the updated Feature vector
Arguments
- gs: The gs Number of Nodes of the Graph (Graph Size)
- param: The Number of Features for each node in the Feature Vector
- a: Size of the abstraction, think of this as the size of a second batch simension
- iterations=1: repeat the Actions of this Layer iterations time
- alinearity=[-1.0,1.0]: activation of this Layer, explained better in glm
- kernel_initializer=”glorot_uniform”: Initializer of this Layer
- self_initializer=None: Instead of using kernel_initializer, this can be used to specify an initializer just for the self interaction of this Layer. Has preference over kernel_initializer.
- neig_initializer=None: Instead of using kernel_initializer, this can be used to specify an initializer just for the neighbour interaction of this Layer. Has preference over kernel_initializer
- learnable=True: weather this Layer has learnable Variables (self and neighbour interaction). Useful for debugging sometimes