ProjectionGraph

A ProjectionGraph represents one of the core structural components of an NGC system. To use a projection graph, Node(s) and Cable(s) must be embedded/integrated into in order to simulate an ancestral projection/sampling process. Note that ProjectionGraph is only useful if an NGCGraph has been created, given that a projection graph is meant to offer non-trainable functionality, particularly fast inference, to an NGC computational system.

Projection Graph

The ProjectionGraph class serves as a core building block for forming a complete NGC computational processing system (particularly with respect to external processes such as projection/sampling).

class ngclearn.engine.proj_graph.ProjectionGraph(name='sampler')

Implements a projection graph – useful for conducting ancestral sampling of a directed generative model or ancestral projection of a clamped graph. Note that when instantiating this object, it is important to call .compile(), like so:

graph = ProjectionGraph(…)

info = graph.compile()

Parameters

name – the name of this projection graph

set_cycle(nodes)

Set execution cycle for this graph

Parameters

nodes – an ordered list of Node(s) to create an execution cycle for

extract(node_name, node_var_name)

Extract a particular signal from a particular node embedded in this graph

Parameters

• node_name – name of the node from the NGC graph to examine

• node_var_name – compartment name w/in Node to extract signal from

Returns

an extracted signal (vector/matrix) OR None if node does not exist

getNode(node_name)

Extract a particular node from this graph

Parameters

node_name – name of the node from the NGC graph to examine

Returns

the desired Node (object)

project(clamped_vars=None, readout_vars=None)

Project signals through the execution pathway(s) defined by this graph

Parameters

• clamped_vars – list of 2-tuples containing named Nodes that will be clamped with particular values. Note that this list takes the form: [(node1_name, node_value1), node2_name, node_value2),…]

• readout_vars – list of 2-tuple strings containing named Nodes and their compartments to read signals from. Note that this list takes the form: [(node1_name, node1_compartment), node2_name, node2_compartment),…]

Returns

readout values - a list of 3-tuples named signals corresponding to the ones in “readout_vars”. Note that

this list takes the form: [(node1_name, node1_compartment, value), node2_name, node2_compartment, value),…]

clear()

Clears/deletes any persistent signals currently embedded w/in this graph’s Nodes