Hierarchical Temporal Memory System with Enhanced Inference Capability
First Claim
1. A node in a computer-implemented hierarchical temporal memory network for generating an output representing causes of input patterns, the node associated with a child node, the node comprising:
- a spatial pooler adapted to generate and store information about spatial co-occurrences of first input patterns received at the node based on spatial similarity of the first input patterns in a learning stage, the spatial pooler generating an output representing probabilities that second input patterns received in an inference stage subsequent to the learning stage correspond to the spatial co-occurrences based on the spatial co-occurrences information, part of the first input patterns and part of the second input patterns received from the child node;
a temporal pooler adapted to generate and store temporal statistics data representing temporal groupings of the spatial co-occurrences based on temporal relationships of the spatial co-occurrences learned in the learning stage; and
a top-down message generator adapted to generate a first top-down message representing information about a state of the node in the inference stage based on the spatial co-occurrences information and the temporal statistics data, the top-down message generator adapted to send the first top-down message to the child node.
1 Assignment
0 Petitions
Accused Products
Abstract
A node, a computer program storage medium, and a method for a hierarchical temporal memory (HTM) network where at least one of its nodes generates a top-down message and sends the top-down message to one or more children nodes in the HTM network. The first top-down message represents information about the state of a node and functions as feedback information from a current node to its child node. The node may also maintain history of the input patterns or co-occurrences so that temporal relationships between input patterns or co-occurrences may be taken into account in an inference stage. By providing the top-town message and maintaining history of previous input patterns, the HTM network may, among others, (i) perform more accurate inference based on temporal history, (ii) make predictions, (iii) discriminate between spatial co-occurrences with different temporal histories, (iv) detect “surprising” temporal patterns, (v) generate examples from a category, and (vi) fill in missing or occluded data.
119 Citations
26 Claims
-
1. A node in a computer-implemented hierarchical temporal memory network for generating an output representing causes of input patterns, the node associated with a child node, the node comprising:
-
a spatial pooler adapted to generate and store information about spatial co-occurrences of first input patterns received at the node based on spatial similarity of the first input patterns in a learning stage, the spatial pooler generating an output representing probabilities that second input patterns received in an inference stage subsequent to the learning stage correspond to the spatial co-occurrences based on the spatial co-occurrences information, part of the first input patterns and part of the second input patterns received from the child node; a temporal pooler adapted to generate and store temporal statistics data representing temporal groupings of the spatial co-occurrences based on temporal relationships of the spatial co-occurrences learned in the learning stage; and a top-down message generator adapted to generate a first top-down message representing information about a state of the node in the inference stage based on the spatial co-occurrences information and the temporal statistics data, the top-down message generator adapted to send the first top-down message to the child node. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A node in a hierarchical temporal memory network between a parent node and a child node, comprising:
-
a spatial pooler adapted to generate and store information about spatial co-occurrences of first input patterns received at the node based on spatial similarity of the first input patterns in a learning stage, the spatial pooler generating an output representing probabilities that second input patterns received in an inference stage subsequent to the learning stage correspond to the spatial co-occurrences based on the spatial co-occurrences information, part of the first input patterns and part of the second input patterns received from the child node; a temporal pooler adapted to generate and store temporal statistics data representing temporal groupings of the spatial co-occurrences based on temporal relationships of the spatial co-occurrences learned in the learning stage; and a bottom-up message generator adapted to generate a first bottom-up message representing information that the second input pattern received at the node in the inference stage corresponds to the learned spatial co-occurrences based on the second input pattern and history of a state of the node in the inference stage, the bottom-up message generator adapted to send the first bottom-up message to the parent node. - View Dependent Claims (10, 11, 12, 13)
-
-
14. A computer program storage medium storing computer instructions adapted to instantiate a node in a hierarchical temporal memory network on a computer, the node associated with a child node in the hierarchical temporal memory network, the computer instructions when executed cause a processor in the computer to:
-
generate and store information about spatial co-occurrences of first input patterns received at the node based on spatial similarity of the first input patterns in a learning stage, part of the first input patterns received from the child node; generate an output representing probabilities that second input patterns received in an inference stage subsequent to the learning stage correspond to the spatial co-occurrences based on the spatial co-occurrences information, part of the second input patterns received from the child node; generate and store temporal statistics data representing temporal groupings of the spatial co-occurrences based on temporal relationships of the spatial co-occurrences learned in the learning stage; generate a first top-down message representing information about a state of the node in the inference stage based on the spatial co-occurrences information and the temporal statistics data; and send the first top-down message to the child node. - View Dependent Claims (15, 16, 17, 18, 19, 20, 21)
-
-
22. A computer program storage medium storing a computer program product including computer instructions adapted to instantiate a node of a hierarchical temporal memory network on a computer, the node between a parent node and a child node in the hierarchical temporal memory network, the computer instructions when executed cause a processor in the computer to:
-
generate and store information about spatial co-occurrences of first input patterns received at the node based on spatial similarity of the first input patterns in a learning stage, part of the first input patterns received from the child node; generating an output representing probabilities that second input patterns received in an inference stage subsequent to the learning stage correspond to the spatial co-occurrences based on the spatial co-occurrences information, part of the second input patterns received from the child node; generate and store temporal statistics data representing temporal groupings of the spatial co-occurrences based on temporal relationships of the spatial co-occurrences learned in the learning stage; generate a first bottom-up message representing information that the second input pattern received at the node in the inference stage corresponds to the learned spatial co-occurrences based on the second input pattern and history of a state of the node in the inference stage; and send the bottom-up message to the parent node. - View Dependent Claims (23, 24, 25, 26)
-
Specification