MULTI-MODAL NEURAL NETWORK FOR UNIVERSAL, ONLINE LEARNING

• US 20130159231A1
• Filed: 08/28/2012
• Published: 06/20/2013
• 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 9,639,802 B2
• Time in Patent Office: Days
• US Class Current: 706/25
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/08 Learning methods

Abstract

In one embodiment, the present invention provides a neural network comprising multiple modalities. Each modality comprises multiple neurons. The neural network further comprises an interconnection lattice for cross-associating signaling between the neurons in different modalities. The interconnection lattice includes a plurality of perception neuron populations along a number of bottom-up signaling pathways, and a plurality of action neuron populations along a number of top-down signaling pathways. Each perception neuron along a bottom-up signaling pathway has a corresponding action neuron along a reciprocal top-down signaling pathway. An input neuron population configured to receive sensory input drives perception neurons along a number of bottom-up signaling pathways. A first set of perception neurons along bottom-up signaling pathways drive a first set of action neurons along top-down signaling pathways. Action neurons along a number of top-down signaling pathways drive an output neuron population configured to generate motor output.

Claims

1. A method, comprising:

interconnecting a plurality of neural nodes via an interconnect network of multiple signaling pathways arranged in a lattice;

wherein interconnecting said plurality of neural nodes includes connecting a plurality of first nodes in a first set of nodes with a plurality of second nodes in a second set of nodes;

each node generating a signal in response to input signals received from one or more other nodes via the interconnect network; and

a connected node in the second set exchanging signals with at least two nodes in the first set via the interconnect network.

2. The method of claim 1, wherein a node comprises one or more neuron populations interconnected via multiple directed edges arranged in an acyclic digraph, wherein each neuron population comprises one or more neurons, and each edge includes a signaling pathway in the interconnect network.

3. The method of claim 2, wherein interconnecting said plurality of neural nodes further includes interconnecting said plurality of neural nodes via bottom-up signaling pathways arranged in an acyclic bottom-up digraph in the interconnect network, each bottom-up signaling pathway including one or more neuron populations and directed edges.

4. The method of claim 3, wherein interconnecting said plurality of neural nodes further includes interconnecting said plurality of neural nodes via top-down signaling pathways arranged in an acyclic top-down digraph in the interconnect network, each top-down signaling pathway including one or more neuron populations and directed edges.

5. The method of claim 4, wherein:

each neuron population in the top-down digraph corresponds to a neuron population in the bottom-up digraph; and

each top-down signaling pathway in the top-down digraph has a reciprocal bottom-up signaling pathway in the bottom-up digraph, such that information flows along said top-down signaling pathway in a first direction, and information flows along said reciprocal bottom-up signaling pathway in a direction opposite of the first direction.

6. The method of claim 5, further comprising:

designating a neuron population at an input periphery of the neural network as an input neuron population configured to receive sensory input, wherein the input neuron population drives neurons along a number of bottom-up signaling pathways;

a first set of neurons along bottom-up signaling pathways driving a first set of neurons along top-down signaling pathways; and

designating a neuron population at an output periphery of the neural network as an output neuron population configured to generate motor output, wherein neurons along a number of top-down signaling pathways drive the output neuron population.

7. The method of claim 6, further comprising:

training each neuron along a bottom-up signaling pathway using a learning rule based on the firing events of said neuron and the firing events of the corresponding neuron along a reciprocal top-down signaling pathway; and

training each neuron along a top-down signaling pathway using a learning rule based on the firing events of said neuron and the firing events of the corresponding neuron along a reciprocal bottom-up signaling pathway.