# US 2016/0260009 A1 · System and method for a recursive cortical network

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0260009 A1
- Document ID: US20160260009A1
- Status: Published application
- Kind: A1
- Application number: 15/158,457
- Filed: 2016-05-18
- Published: 2016-09-08
- Earliest claimed: 2012-05-15
- Assignees: Vicarious FPC, Inc.
- Applicants: Vicarious FPC, Inc.
- Inventors: Dileep George; Kenneth Kansky; D Scott Phoenix; Bhaskara Marthi; Christopher Laan; Wolfgang Lehrach
- Web page: https://patentgrep.com/patent/US20160260009A1

## CPC

- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/0475: Generative networks
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 20/00: Machine learning
- G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G06N 5/04: Inference or reasoning models
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system includes: a recursively architected network of sub-networks organized into a hierarchical layers; the sub-networks including at least a parent feature node, a pool node, a parent-specific child feature (PSCF) node, and a child feature node; the parent feature node of at least one sub-network configured with a selection function actionable on at least two pool nodes connected to the parent feature node of the at least one sub-network; the pool node of the at least one sub-network configured with a selection function actionable on at least two PSCF nodes connected to the pool node of the at least one sub-network; the PSCF node of the at least one sub-network configured to activate a connected child feature node; the child feature node connectable to at least a parent feature node of a sub-network at a lower hierarchical layer.

## Claims

### Claim 1

A system comprising:
a recursively architected network of sub-networks organized into a plurality of hierarchical layers;
the sub-networks comprising at least a parent feature node, a pool node, a parent-specific child feature (PSCF) node, and a child feature node;
the parent feature node of at least one sub-network configured with a selection function actionable on at least two pool nodes connected to the parent feature node of the at least one sub-network;
the pool node of the at least one sub-network configured with a selection function actionable on at least two PSCF nodes connected to the pool node of the at least one sub-network;
the PSCF node of the at least one sub-network configured to activate a connected child feature node;
the child feature node connectable to at least a parent feature node of a sub-network at a lower hierarchical layer.

### Claim 2 (depends on 1)

The system of claim 1, further comprising a constraint node with at least two connections from at least two PSCF nodes, with a selection function to augment selection by the pool node.

### Claim 3 (depends on 2)

The system of claim 2, wherein the constraint node is connected to a first PCSF node and a second PCSF node, wherein the first PCSF node is connected to a first pool node and the second PCSF node is connected to a second pool node.

### Claim 4 (depends on 3)

The system of claim 3, wherein the first pool node and the second pool node are connected to a single shared parent feature node; wherein the first pool node and the second node are contained within a single sub-network.

### Claim 5 (depends on 3)

The system of claim 3, wherein the first pool node is connected to a first parent feature node and is contained within a first sub-network; wherein the second pool node is connected to a second parent feature node and is contained within the second sub-network, distinct from the first sub-network.

### Claim 6 (depends on 5)

The system of claim 5, wherein the first sub-network is at a different hierarchical level than the second sub-network.

### Claim 7 (depends on 1)

The system of claim 1, wherein nodes of the network are configured with posterior distribution components; wherein the network is configured to propagate node activation through the plurality of hierarchical layers in a manner consistent with node connections of sub-networks of the network and the posterior distribution components.

### Claim 8 (depends on 7)

The system of claim 7, wherein the network is configured to output parent feature node selection as an inferred output in response to receiving data feature input at at least one child feature node.

### Claim 9 (depends on 8)

The system of claim 8, wherein the network is configured to propagate node activation by:
at child feature nodes, messaging a likelihood score to connected parent-specific child feature (PSCF) nodes;
at a pool node of a sub-network, generating a likelihood score from a posterior distribution component and the likelihood score of connected PSCF nodes;
at a parent feature node of the sub-network, generating a likelihood score from the posterior distribution component and the likelihood score of pool nodes connected to the parent feature node.

### Claim 10 (depends on 8)

The system of claim 8, wherein the network is configured to receive data feature input by setting activation of child feature nodes according to image features of an image; wherein the inferred output includes a classification of the image.

### Claim 11 (depends on 8)

system of claim 8, wherein the network is configured to receive data feature input by setting activation of child feature nodes according to audio features of an audio signal; wherein the inferred output includes a classification of the audio signal.

### Claim 12 (depends on 7)

The system of claim 7, wherein the network is configured to output child feature node selection as a generated output in response to received parent feature input.

### Claim 13 (depends on 12)

The system of claim 12, wherein the generated output is an image generated based on a mapping of selected child feature nodes to image features.

### Claim 14 (depends on 13)

The system of claim 13, wherein the parent feature input is an image classification.

### Claim 15 (depends on 12)

The system of claim 12, wherein the generated output is an audio signal generated based on a mapping of selected child feature nodes to audio features.

### Claim 16 (depends on 13)

The system of claim 13, wherein the parent feature input is an audio signal classification.

### Claim 17 (depends on 12)

The system of claim 12, wherein the network is further configured to receive seed child feature input; wherein the seed child feature input is used by the network to modify the generated output.

### Claim 18 (depends on 17)

The system of claim 17, wherein the network is configured to receive seed child feature input by setting activation of seeded child feature nodes.

### Claim 19 (depends on 18)

The system of claim 18, wherein the network is configured to output child feature node selection as a generated output in response to both of the received parent feature input and the seed child feature input.

### Claim 20 (depends on 19)

The system of claim 19, wherein the network is configured to set activation of the seeded child feature nodes according to image features of a first portion of an image; wherein the generated output is a second portion of the image.

### Claim 21 (depends on 1)

The system of claim 1, wherein the child feature node is connected to a plurality of parent feature nodes of sub-networks at a lower hierarchical level.

### Claim 22 (depends on 21)

The system of claim 21, wherein evidence presented to the child feature node is processed by applying a noisy-OR gate to evidence transmitted by a first parent feature node of the plurality of parent feature nodes and evidence transmitted by a second parent feature node of the plurality of parent feature nodes.

### Claim 23 (depends on 21)

The system of claim 21, wherein evidence presented to the child feature node is processed by applying a noisy-MAX gate to evidence transmitted by a first parent feature node of the plurality of parent feature nodes and evidence transmitted by a second parent feature node of the plurality of parent feature nodes.

### Claim 24 (depends on 1)

The system of claim 1, wherein the network is implemented by a recursive cortical network operating on an electronic computing system.
