System and method for a recursive cortical network
A method for generating patterns with a network includes providing a recursive network of sub-networks with a parent feature node and at least two child feature nodes; and at a first sub-network of the recursive network, the first sub-network including the parent feature node and the at least two child feature nodes, selecting a first pool node and a second pool node consistent with a selection function of the parent feature node, selecting at least a first parent-specific child feature (PSCF) node that corresponds to a first child feature node of the sub-network, selecting at least a second parent-specific child feature (PSCF) node that corresponds to a second child feature node of the sub-network; and compiling the state of final child feature nodes, including the first and second child feature nodes, of the network into a generated output.
1. A method for generating patterns with a network comprising:
providing a recursive network of sub-networks with a parent feature node and at least two child feature nodes; wherein the parent feature node is an input node and the at least two child feature nodes are output nodes;
propagating node selection down the network layer hierarchy in a manner consistent with node connections of sub-networks of the network, propagation within the sub-networks comprising:
at an activated parent feature node of a sub-network, selecting a pool node consistent with a selection function of the parent feature node;
at the pool node of a first pool, selecting at least a first parent-specific child feature (PSCF) node that corresponds to a child feature node of the sub-network; and
in response to the selection of a first node of the sub-network, enforcing a selection constraint on at least a second node of a second pool according to a lateral constraint node of the sub-network; and
compiling the state of final child feature nodes of the network into a generated output.
2. The method of claim 1 , wherein the first node is the first PSCF node, and the second node of the second pool is a PSCF node.
3. The method of claim 2 , wherein the second PSCF node of the second pool is within the sub-network of the first node.
4. The method of claim 2 , wherein the second PSCF node of the second pool is in a second sub-network.
5. The method of claim 2 , wherein the first PSCF node is in a network of a first time instant and the second PSCF node of the second pool is in a network of a second time instant.
6. The method of claim 2 , further comprising in response to selecting the PSCF node selecting at least one child feature node, mapping selected child feature nodes to data features that are compiled into the generated output.
7. The method of claim 6 , wherein the generated output is an image.
8. The method of claim 6 , wherein the generated output is a sequence of images.
9. The method of claim 6 , wherein the generated output is audio.
10. The method of claim 6 , wherein the selection function is a Boolean logical selection function.
11. The method of claim 10 , wherein the child feature nodes of a first layer sub-network are the parent feature nodes for at least two sub-networks in a second layer.
12. The method of claim 11 , wherein selecting the pool node consistent with a selection function comprises selecting each pool node connected to the parent node according to a logical AND selection function; wherein selecting the first PSCF node comprises randomly selecting only one PSCF node from the set of PSCF nodes connected to the pool node according to a logical XOR selection function of the pool node.
13. The method of claim 11 , wherein selecting at least a first PSCF node further comprises randomly selecting a first subset of PSCF nodes from the set of PSCF nodes connected to the pool node according to a logical XOR selection function of the pool node, the selection function applied to a plurality of subsets of the set of PSCF nodes.
14. The method of claim 13 , wherein selecting the pool node consistent with a selection function comprises selecting each pool node connected to the parent node according to a logical AND selection function.
15. A method for generating patterns with a network comprising:
providing a recursive network of sub-networks with a parent feature node and at least two child feature nodes; wherein the parent feature node is an input node and the at least two child feature nodes are output nodes; and
at a first sub-network of the recursive network, the first sub-network including the parent feature node and the at least two child feature nodes:
at an activated parent feature node of the first sub-network, selecting a first pool node and a second pool node consistent with a selection function of the parent feature node;
at the first pool node, selecting at least a first parent-specific child feature (PSCF) node that corresponds to a first child feature node of the sub-network;
at the second pool node, selecting at least a second parent-specific child feature (PSCF) node that corresponds to a second child feature node of the sub-network; and
compiling the state of final child feature nodes, including the first and second child feature nodes, of the network into a generated output.
16. The method of claim 15 , further comprising in response to selecting the first and second PSCF nodes, mapping selected child feature nodes to data features that are compiled into the generated output.
17. The method of claim 16 , wherein the generated output is an image.
18. The method of claim 16 , wherein the generated output is a sequence of images.
19. The method of claim 16 , wherein the generated output is audio.
20. The method of claim 15 , further comprising: at the first pool node, selecting at least a third parent-specific child feature (PSCF) node that corresponds to a third child feature node of the sub-network; wherein the first and third PSCF nodes are selected according to a logical XOR selection function of the first pool node applied across subsets of a set of PSCF nodes connected to the first pool node.