Hierarchical temporal memory system with higher-order temporal pooling capability
First Claim
1. A node in a computer-implemented Temporal Memory network, the node comprising:
- a processor;
a temporal pooler configured to generate temporal statistics data representing a higher than first order Markov chain of temporal sequences of the spatial co-occurrences based on temporal relationships of the spatial co-occurrences of first input patterns in the training stage; and
an inference engine configured to generate an output based on the temporal statistics data responsive to receiving a sequence of spatial co-occurrence information about second input patterns in an inference stage subsequent to the training stage, the output representing probabilities of the sequence of the spatial co-occurrence information corresponding to temporal sequences of the temporal statistics data.
2 Assignments
0 Petitions
Accused Products
Abstract
A temporal pooler for a Hierarchical Temporal Memory network is provided. The temporal pooler is capable of storing information about sequences of co-occurrences in a higher-order Markov chain by splitting a co-occurrence into a plurality of sub-occurrences. Each split sub-occurrence may be part of a distinct sequence of co-occurrences. The temporal pooler receives the probability of spatial co-occurrences in training patterns and tallies counts or frequency of transitions from one sub-occurrence to another sub-occurrence in a connectivity matrix. The connectivity matrix is then processed to generate temporal statistics data. The temporal statistics data is provided to an inference engine to perform inference or prediction on input patterns. By storing information related to a higher-order Markov model, the temporal statistics data more accurately reflects long temporal sequences of co-occurrences in the training patterns.
-
Citations
20 Claims
-
1. A node in a computer-implemented Temporal Memory network, the node comprising:
-
a processor; a temporal pooler configured to generate temporal statistics data representing a higher than first order Markov chain of temporal sequences of the spatial co-occurrences based on temporal relationships of the spatial co-occurrences of first input patterns in the training stage; and an inference engine configured to generate an output based on the temporal statistics data responsive to receiving a sequence of spatial co-occurrence information about second input patterns in an inference stage subsequent to the training stage, the output representing probabilities of the sequence of the spatial co-occurrence information corresponding to temporal sequences of the temporal statistics data. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A computer-implemented method of generating an output in a node of a Temporal Memory network, comprising:
-
generating information about spatial co-occurrences of first input patterns received by the node based on spatial similarity of the first input patterns in a training stage; generating temporal statistics data representing a higher than first order Markov chain of temporal sequences of the spatial co-occurrences based on temporal relationships of the spatial co-occurrences in the training stage; and generating the output based on the temporal statistics data responsive to receiving a sequence of spatial co-occurrence information about second input patterns, the output representing probabilities of the sequence of the spatial co-occurrence information corresponding to temporal sequences of the temporal statistics data in an inference stage subsequent to the training stage. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17)
-
-
18. A non-transitory computer program storage medium storing computer instructions to operate a Temporal Memory network on a computer, the computer instructions when executed cause a processor in the computer to:
-
generate information about spatial co-occurrences of first input patterns received by a node in the Temporal Memory system based on spatial similarity of the first input patterns in a training stage; generate temporal statistics data representing a higher than first order Markov chain of temporal sequences of the spatial co-occurrences based on temporal relationships of the spatial co-occurrences in the training stage; and generate an output based on the temporal statistics data responsive to receiving a sequence of spatial co-occurrence information about second input patterns, the output representing probabilities of the sequence of the spatial co-occurrence information corresponding to temporal sequences of the temporal statistics data in an inference stage subsequent to the training stage. - View Dependent Claims (19, 20)
-
Specification