Back to results
US 2015/0088796 A1Published application
Methods and apparatus for implementation of group tags for neural models
AssigneeQUALCOMM Incorporated
InventorsDavid Jonathan JULIAN, Jeffrey Alexander LEVIN, Jeffrey Baginsky GEHLHAAR
Life of this patent
Estimating the term…
Abstract
Certain aspects of the present disclosure support assigning neurons and/or synapses to group tags where group tags have an associated set of parameters. By using group tags, neurons or synapses in a population can be assigned a group tag. Then, by changing a parameter associated with the group tag, all synapses or neurons in the group may have that parameter changed.
Claims29
A method for operating an artificial nervous system, comprising:
- assigning at least one of a first population of synapses or a first population of artificial neurons of the artificial nervous system to a first group tag, wherein the first group tag is associated with a first set of parameters and at least one of a first synapse type or a first neuron type;
- assigning at least one of a second population of synapses or a second population of artificial neurons of the artificial nervous system to a second group tag, wherein the second group tag is associated with a second set of parameters and at least one of a second synapse type or a second neuron type;
- and
- changing one or more parameters in at least one of the first set of parameters or the second set of parameters causing changing the one or more parameters for at least one of:
- one or more synapses in at least one of the first population or the second population, or one or more artificial neurons in at least one of the first population or the second population.
2 more elements
The method of 1, wherein at least one of the first group tag or the second group tag is assigned dynamically.
An apparatus for operating an artificial nervous system, comprising:
- a processing system configured to:
- assign at least one of a first population of synapses or a first population of artificial neurons of the artificial nervous system to a first group tag, wherein the first group tag is associated with a first set of parameters and at least one of a first synapse type or a first neuron type;
- assign at least one of a second population of synapses or a second population of artificial neurons of the artificial nervous system to a second group tag, wherein the second group tag is associated with a second set of parameters and at least one of a second synapse type or a second neuron type;
- and
- change one or more parameters in at least one of the first set of parameters or the second set of parameters causing changing the one or more parameters for at least one of:
- one or more synapses in at least one of the first population or the second population, or one or more artificial neurons in at least one of the first population or the second population;
- and
- a memory coupled to the processing system.
5 more elements
An apparatus for operating an artificial nervous system, comprising:
- means for assigning at least one of a first population of synapses or a first population of artificial neurons of the artificial nervous system to a first group tag, wherein the first group tag is associated with a first set of parameters and at least one of a first synapse type or a first neuron type;
- means for assigning at least one of a second population of synapses or a second population of artificial neurons of the artificial nervous system to a second group tag, wherein the second group tag is associated with a second set of parameters and at least one of a second synapse type or a second neuron type;
- and
- means for changing one or more parameters in at least one of the first set of parameters or the second set of parameters causing changing the one or more parameters for at least one of:
- one means for or more synapses in at least one of the first population or the second population, or one or more artificial neurons in at least one of the first population or the second population.
2 more elements
A computer program product for operating an artificial nervous system, comprising a computer-readable medium having instructions executable to:
- assign at least one of a first population of synapses or a first population of artificial neurons of the artificial nervous system to a first group tag, wherein the first group tag is associated with a first set of parameters and at least one of a first synapse type or a first neuron type;
- assign at least one of a second population of synapses or a second population of artificial neurons of the artificial nervous system to a second group tag, wherein the second group tag is associated with a second set of parameters and at least one of a second synapse type or a second neuron type;
- and
- change one or more parameters in at least one of the first set of parameters or the second set of parameters causing changing the one or more parameters for at least one of:
- one or more synapses in at least one of the first population or the second population, or one or more artificial neurons in at least one of the first population or the second population.
2 more elements
A method for operating an artificial nervous system, comprising:
- assigning a group of artificial neurons and synapses of the artificial nervous system to a group tag with an associated set of parameters;
- and
- sending a single message changing values of the parameters in the set causing simultaneous switch of the parameters for all artificial neurons and synapses in the group.
An apparatus for operating an artificial nervous system, comprising:
- a processing system configured to:
- assign a group of artificial neurons and synapses of the artificial nervous system to a group tag with an associated set of parameters;
- and
- send a single message changing values of the parameters in the set causing simultaneous switch of the parameters for all artificial neurons and synapses in the group;
- and
- a memory coupled to the processing system.
3 more elements
An apparatus for operating an artificial nervous system, comprising:
- means for assigning a group of artificial neurons and synapses of the artificial nervous system to a group tag with an associated set of parameters;
- and
- means for sending a single message changing values of the parameters in the set causing simultaneous switch of the parameters for all artificial neurons and synapses in the group.
A computer program product for operating an artificial nervous system, comprising a computer-readable medium having instructions executable to:
- assign a group of artificial neurons and synapses of the artificial nervous system to a group tag with an associated set of parameters;
- and
- send a single message changing values of the parameters in the set causing simultaneous switch of the parameters for all artificial neurons and synapses in the group.
Dependencies are inferred from the claim text.