UNIVERSAL, ONLINE LEARNING IN MULTI-MODAL PERCEPTION-ACTION SEMILATTICES

• US 20140019393A1
• Filed: 12/14/2011
• Published: 01/16/2014
• Est. Priority Date: 12/14/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Modha, Dharmendra S.
• Granted Patent: US 8,799,199 B2
• Time in Patent Office: Days
• US Class Current: 706/29
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/049 Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
• CPC Class Codes: G06N 3/10 Interfaces, programming languages or software development kits, e.g. for simulating neural networks

Abstract

In one embodiment, the present invention provides a method for interconnecting neurons in a neural network. At least one node among a first set of nodes is interconnected to at least one node among a second set of nodes, and nodes of the first and second set are arranged in a lattice. At least one node of the first set represents a sensory-motor modality of the neural network. At least one node of the second set is a union of at least two nodes of the first set. Each node in the lattice has an acyclic digraph comprising multiple vertices and directed edges. Each vertex represents a neuron population. Each directed edge comprises multiple synaptic connections. Vertices in different acyclic digraphs are interconnected using an acyclic bottom-up digraph. The bottom-up digraph has a corresponding acyclic top-down digraph. Vertices in the bottom-up digraph are interconnected to vertices in the top-down digraph.

Claims

1-26. -26. (canceled)

27. A signaling interconnect for neural nodes, comprising:

an interconnection lattice that interconnects a plurality of first nodes in a first set of nodes with a plurality of second nodes in a second set of nodes, wherein the connected nodes are arranged in a lattice such that a connected node in the second set is a union of at least two nodes in the first set, and said connected node exchanges signals with said at least two nodes via the interconnection lattice.

28. The signaling interconnect of claim 27, wherein:

a node comprises one or more neural vertices interconnected via multiple directed edges arranged in an acyclic digraph, wherein each neural vertex comprises one or more neurons, and each edge comprises a signaling pathway in the interconnection lattice.

29. The signaling interconnect of claim 28, wherein:

the interconnection lattice interconnects said nodes via bottom-up signaling pathways arranged in an acyclic bottom-up digraph in the interconnection lattice, each bottom-up signaling pathway including one or more vertices and directed edges; and

the interconnection lattice further interconnects said nodes via top-down signaling pathways arranged in an acyclic top-down digraph in the interconnection lattice, each top-down signaling pathway including one or more vertices and directed edges;

wherein a sending vertex of a first node is interconnected to a receiving vertex of a second node only if the second node is a superset of the first node;

wherein each vertex in the top-down digraph corresponds to a vertex in the bottom-up digraph; and

wherein each directed edge in the top-down digraph corresponds to a directed edge in the bottom-up digraph, such that information flows along said directed edge in the top-down digraph in a first direction, and information flows along said corresponding directed edge in the bottom-up digraph in a direction opposite of the first direction.

30. The signaling interconnect of claim 29, further comprising additional directed edges that

interconnect vertices in the bottom-up digraph to vertices in the top-down digraph.

31. The signaling interconnect of claim 30, wherein a sending vertex in the bottom-up

digraph is interconnected to a receiving vertex in the top-down digraph if an intersection of the node comprising the sending vertex and the node comprising the receiving vertex is empty.

32. The signaling interconnect of claim 30, wherein a sending vertex in the bottom-up digraph is interconnected to a receiving vertex in the top-down digraph if the sending vertex and the receiving vertex correspond to one another.

33. The signaling interconnect of claim 30, wherein:

vertices that do not have incoming directed edges are designated as source vertices;

vertices that do not have outgoing directed edges are designated as sink vertices;

a source vertex in the bottom-up digraph is configured to receive sensory input;

a sink vertex in the top-down digraph is configured to generate motor output;

for each sink vertex in the bottom-up digraph, said sink vertex in the bottom-up digraph is interconnected to a vertex in the top-down digraph via at least one outgoing directed edge from said sink vertex; and

for each source vertex in the top-down digraph, a vertex in the bottom-up digraph is interconnected to said source vertex in the top-down digraph via at least one incoming directed edge to said source vertex.

34. The signaling interconnect of claim 30, wherein:

for each vertex, a first set and a second set of neurons in said vertex are good neurons and bad neurons, respectively, such that the number of good neurons in said vertex is the same as the number of bad neurons in said vertex;

wherein each good neuron in a vertex in the top-down digraph corresponds to a bad neuron in said vertex, a good neuron in a corresponding vertex in the bottom-down digraph, and a bad neuron in the corresponding vertex in the bottom-down digraph.

35. The signaling interconnect of claim 34, wherein:

vertices that do not have incoming directed edges are designated as source vertices;

vertices that do not have outgoing directed edges are designated as sink vertices; and

for each good neuron in a sink vertex in the top-down digraph;

said good neuron is connected to an evaluation module, wherein the evaluation module determines whether output from said good neuron is good or bad, such that good output from said good neuron is connected to a corresponding good neuron in a corresponding source vertex in the bottom-up digraph, and bad output from said good neuron is connected to a corresponding bad neuron in the corresponding source vertex in the bottom-up digraph.

36. The signaling interconnect of claim 33, wherein:

each node has a sensory or motor modality;

each directed edge interconnecting a sending vertex to a receiving vertex comprises multiple synaptic connections such that a neuron in the receiving vertex receives synaptic connections from a subset of neurons in the sending vertex; and

some acyclic digraphs are empty.

37. A computer program product on a computer-readable medium for interconnecting neural nodes arranged in an interconnection lattice such that a connected node exchanges signals with at least two other nodes via the interconnection lattice, wherein a node comprises one or more neural vertices interconnected via multiple directed edges arranged in an acyclic digraph, each neural vertex comprising one or more neurons, each edge comprising a signaling pathway in the interconnection lattice, the computer program product comprising instructions, which when executed on a computer cause the computer to perform operations including:

connecting said nodes via bottom-up signaling pathways arranged in an acyclic bottom-up digraph in the interconnection lattice, each bottom-up signaling pathway including one or more vertices and directed edges;

connecting said nodes via top-down signaling pathways arranged in an acyclic top-down digraph in the interconnection lattice, each top-down signaling pathway including one or more vertices and directed edges, wherein each vertex in the top-down digraph corresponds to a vertex in the bottom-up digraph, wherein each directed edge in the top-down digraph corresponds to a directed edge in the bottom-up digraph, such that information flows along said directed edge in the top-down digraph in a first direction, and information flows along said corresponding directed edge in the bottom-up digraph in a direction opposite of the first direction; and

interconnecting vertices in the bottom-up digraph to vertices in the top-down digraph using additional directed edges.