Neural network learning and collaboration apparatus and methods
First Claim
1. A non-transitory computer readable medium configured to store at least one computer program thereon, the computer program comprising a plurality of instructions configured to when executed:
- establish a data connection to a synaptic device;
receive status information from the synaptic device;
issue a command to the synaptic device, the synaptic device being configured to execute an action based at least in part on the command;
receive feedback input from a user; and
forward the feedback input to the synaptic device via the data connection;
wherein;
the forwarding of the feedback input causes the synaptic device to alter a behavioral trait;
the alteration of the behavioral trait comprises an adjustment of a configuration of an artificial neural network disposed at least in part on the synaptic device, the artificial neural network being comprised of a plurality of spiking neurons; and
the alteration of the behavioral trait comprises at least one of (i) a potentiation or (ii) a depression of a subset of the plurality of spiking neurons.
2 Assignments
0 Petitions
Accused Products
Abstract
Apparatus and methods for learning and training in neural network-based devices. In one implementation, the devices each comprise multiple spiking neurons, configured to process sensory input. In one approach, alternate heterosynaptic plasticity mechanisms are used to enhance learning and field diversity within the devices. The selection of alternate plasticity rules is based on recent post-synaptic activity of neighboring neurons. Apparatus and methods for simplifying training of the devices are also disclosed, including a computer-based application. A data representation of the neural network may be imaged and transferred to another computational environment, effectively copying the brain. Techniques and architectures for achieve this training, storing, and distributing these data representations are also disclosed.
72 Citations
26 Claims
-
1. A non-transitory computer readable medium configured to store at least one computer program thereon, the computer program comprising a plurality of instructions configured to when executed:
-
establish a data connection to a synaptic device; receive status information from the synaptic device; issue a command to the synaptic device, the synaptic device being configured to execute an action based at least in part on the command; receive feedback input from a user; and forward the feedback input to the synaptic device via the data connection; wherein; the forwarding of the feedback input causes the synaptic device to alter a behavioral trait; the alteration of the behavioral trait comprises an adjustment of a configuration of an artificial neural network disposed at least in part on the synaptic device, the artificial neural network being comprised of a plurality of spiking neurons; and the alteration of the behavioral trait comprises at least one of (i) a potentiation or (ii) a depression of a subset of the plurality of spiking neurons. - View Dependent Claims (2, 3, 22)
-
-
4. A training device configured to manage activity in at least one spiking neural network comprising a plurality of spiking neurons, the training device comprising:
-
at least one network interface configured to; establish an operative link to the at least one spiking neural network; receive one or more activity indicators associated with the at least one spiking neural network; and transmit feedback input to the at least one spiking neural network; a user interface configured to; based at least in part on the one or more activity indicators, display one or more human perceptible signals; and provide a user with at least one menu from which to select training options; and logic in operative communication with the user interface and the at least one network interface, the logic configured to process a selected training option to generate the feedback input; wherein the transmission of the feedback input is configured to depress at least a portion of the plurality of spiking neurons. - View Dependent Claims (5, 6, 7, 8)
-
-
9. A method of managing activity within a spiking neural network, the method comprising:
-
establishing a data link to a user interface device; sending one or more status updates related to a plurality of activity states of neurons in the spiking neural network; receiving, via the link, one or more feedback indicators, the one or more feedback indicators being based at least on part on a selected training option from the user interface device; and based on at least one rule, associating the one or more feedback indicators with a subset of the neurons in the spiking neural network; wherein associating the one or more feedback indicators comprises potentiating the subset of neurons. - View Dependent Claims (10, 11)
-
-
12. A computerized neuromorphic apparatus comprising:
-
one or more functional modules; a network interface configured to establish a link to a training device; and logic configured to; send, to the training device, status indicators related to a neural network disposed at least in part on the computerized neuromorphic apparatus; receive feedback based on a selected one or more of a plurality of available management options; and alter a state of one or more of a neuron and a connection in accordance with the feedback and at least one timing rule; wherein; a magnitude and a direction of the alteration are based on at least the feedback; and a target of the alteration is selected based on the at least one timing rule. - View Dependent Claims (14, 15, 16, 17)
-
-
13. A computerized neuromorphic apparatus comprising:
-
one or more functional modules; a network interface configured to establish a link to a training device; and logic configured to; send, to the training device, status indicators related to a neural network disposed at least in part on the computerized neuromorphic apparatus; receive feedback based on a selected one or more of a plurality of available management options; and alter a state of one or more of a neuron and a connection in accordance with the feedback and at least one timing rule; wherein; the status indicators comprise an identified action and an identifier for one or more contributory neurons; and the plurality of available management options comprise a positive feedback option and a negative feedback option. - View Dependent Claims (18, 19)
-
-
20. A computerized neuromorphic apparatus comprising:
-
one or more functional modules; a remote interface configured to establish a link to a training device; and logic configured to; send, to the training device, status indicators related to a neural network disposed at least in part on the computerized neuromorphic apparatus; receive feedback based on a selected one or more of a plurality of available management options; and alter a state of one or more of a neuron and a connection in accordance with the feedback and at least one timing rule; wherein one or more feedback elements comprise positive feedback to potentiate one or more neurons of the neural network. - View Dependent Claims (21, 23, 24, 25, 26)
-
Specification