Abstract: Apparatus and methods for activity based plasticity in a spiking neuron network adapted to process sensory input. In one embodiment, the plasticity mechanism may be configured for example based on activity of one or more neurons providing feed-forward stimulus and activity of one or more neurons providing inhibitory feedback. When an inhibitory neuron generates an output, inhibitory connections may be potentiated. When an inhibitory neuron receives inhibitory input, the inhibitory connection may be depressed. When the inhibitory input arrives subsequent to the neuron response, the inhibitory connection may be depressed. When input features are unevenly distributed in occurrence, the plasticity mechanism is capable of reducing response rate of neurons that develop receptive fields to more prevalent features. Such functionality may provide network output such that rarely occurring features are not drowned out by more widespread stimulus.

Abstract: Generalized state-dependent learning framework in artificial neuron networks may be implemented. A framework may be used to describe plasticity updates of neuron connections based on connection state term and neuron state term. The state connections within the network may be updated based on inputs and outputs to/from neurons. The input connections of a neuron may be updated using connection traces comprising a time-history of inputs provided via the connections. Weights of the connections may be updated and connection state may be time varying. The updated weights may be determined using a rate of change of the trace and a term comprising a product of a per-neuron contribution and a per-connection contribution configured to account for the state time-dependency. Using event-dependent connection change components, connection updates may be executed on per neuron basis, as opposed to per-connection basis.

Abstract: A robotic device may comprise an adaptive controller configured to learn to predict consequences of robotic device's actions. During training, the controller may receive a copy of the planned and/or executed motor command and sensory information obtained based on the robot's response to the command. The controller may predict sensory outcome based on the command and one or more prior sensory inputs. The predicted sensory outcome may be compared to the actual outcome. Based on a determination that the prediction matches the actual outcome, the training may stop. Upon detecting a discrepancy between the prediction and the actual outcome, the controller may provide a continuation signal configured to indicate that additional training may be utilized. In some classification implementations, the discrepancy signal may be used to indicate occurrence of novel (not yet learned) objects in the sensory input and/or indicate continuation of training to recognize said objects.

Abstract: Apparatus and methods for training of robotic devices. A robot may be trained by a user guiding the robot along target trajectory using a control signal. A robot may comprise an adaptive controller. The controller may be configured to generate control commands based on the user guidance, sensory input and a performance measure. A user may interface to the robot via an adaptively configured remote controller. The remote controller may comprise a mobile device, configured by the user in accordance with phenotype and/or operational configuration of the robot. The remote controller may detect changes in the robot phenotype and/or operational configuration. User interface of the remote controller may be reconfigured based on the detected phenotype and/or operational changes.

Abstract: Apparatus and methods for processing inputs by one or more neurons of a network. The neuron(s) may generate spikes based on receipt of multiple inputs. Latency of spike generation may be determined based on an input magnitude. Inputs may be scaled using for example a non-linear concave transform. Scaling may increase neuron sensitivity to lower magnitude inputs, thereby improving latency encoding of small amplitude inputs. The transformation function may be configured compatible with existing non-scaling neuron processes and used as a plug-in to existing neuron models. Use of input scaling may allow for an improved network operation and reduce task simulation time.

Abstract: Apparatus and methods for feedback in a spiking neural network. In one approach, spiking neurons receive sensory stimulus and context signal that correspond to the same context. When the stimulus provides sufficient excitation, neurons generate response. Context connections are adjusted according to inverse spike-timing dependent plasticity. When the context signal precedes the post synaptic spike, context synaptic connections are depressed. Conversely, whenever the context signal follows the post synaptic spike, the connections are potentiated. The inverse STDP connection adjustment ensures precise control of feedback-induced firing, eliminates runaway positive feedback loops, enables self-stabilizing network operation. In another aspect of the invention, the connection adjustment methodology facilitates robust context switching when processing visual information. When a context (such an object) becomes intermittently absent, prior context connection potentiation enables firing for a period of time.

Abstract: Apparatus and methods for salient feature detection by a spiking neuron network. The network may comprise feature-specific units capable of responding to different objects (red and green color). The plasticity mechanism of the network may be configured based on difference between two similarity measures related to activity of different unit types obtained during network training. One similarity measure may be based on activity of units of the same type (red). Another similarity measure may be based on activity of units of one type (red) and another type (green). Similarity measures may comprise a cross-correlogram and/or mutual information determined over an activity window. During network operation, the activity based plasticity mechanism may be used to potentiate connections between units of the same type (red-red). The plasticity mechanism may be used to depress connections between units of different types (red-green). The plasticity mechanism may effectuate detection of salient features in the input.

Abstract: Apparatus and methods for universal node design implementing a universal learning rule in a mixed signal spiking neural network. In one implementation, at one instance, the node apparatus, operable according to the parameterized universal learning model, receives a mixture of analog and spiking inputs, and generates a spiking output based on the model parameter for that node that is selected by the parameterized model for that specific mix of inputs. At another instance, the same node receives a different mix of inputs, that also may comprise only analog or only spiking inputs and generates an analog output based on a different value of the node parameter that is selected by the model for the second mix of inputs. In another implementation, the node apparatus may change its output from analog to spiking responsive to a training input for the same inputs.

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.

Abstract: Robotic devices may be trained using saliency maps derived from gaze of a trainer. In navigation applications, the saliency map may correspond to portions of the environment being observed by a driving instructor during training using a gaze detector. During an operation, a driver assist robot may utilize the saliency map in order to assess attention of the driver, detect potential hazards, and issue alerts. Responsive to a detection of a mismatch between the driver current attention and the target attention derived from the saliency map, the robot may issue a warning, and/or prompt the driver of an upcoming hazard. A data processing apparatus may employ gaze based saliency maps in order to analyze, e.g., surveillance camera feeds for intruders, open doors, hazards, policy violations (e.g., open doors).

Abstract: Spiking neuron network conditionally independent subset classifier apparatus and methods. In some implementations, the network may comprise one or more subset neuron layers configured to determine presence of one or more features in the subset of plurality of conditionally independent features. The output of the subset layer may be coupled to an aggregation layer. State of the subset layer may be configured during training based on training input and a reference signal. During operation, spiking output of the subset layer may be combined by the aggregation layer to produce classifier output. Subset layer output and/or classifier output may be encoded using spike rate, latency, and/or base-n encoding.

Abstract: Optical flow for a moving platform may be encoded into pulse output. Optical flow contribution induced due to the platform self-motion may be cancelled. The cancellation may be effectuated by (i) encoding the platform motion into pulse output; and (ii) inhibiting pulse generation by neurons configured to encode optical flow component optical flow that occur based on self-motion. The motion encoded may be coupled to the optical flow encoder via one or more connections. Connection propagation delay may be configured during encoder calibration in the absence of obstacles so as to provide system specific delay matrix. The inhibition may be based on a coincident arrival of the motion spiking signal via the calibrated connections to the optical flow encoder neurons. The coincident motion pulse arrival may be utilized in order to implement an addition of two or more vector properties.

Abstract: Adaptive controller apparatus of a plant may be implemented. The controller may comprise an encoder block and a control block. The encoder may utilize basis function kernel expansion technique to encode an arbitrary combination of inputs into spike output. The controller may comprise spiking neuron network operable according to reinforcement learning process. The network may receive the encoder output via a plurality of plastic connections. The process may be configured to adaptively modify connection weights in order to maximize process performance, associated with a target outcome. The relevant features of the input may be identified and used for enabling the controlled plant to achieve the target outcome. The stochasticity of the learning process may be modulated. Stochasticity may be increased during initial stage of learning in order to encourage exploration. During subsequent controller operation, stochasticity may be reduced to reduce energy use by the controller.

Abstract: Apparatus and methods for controlling attention and training of autonomous robotic devices. In one approach, attention of the robot may be manipulated by use of a spot-light device illuminating a portion of the aircraft undergoing inspection in order to indicate to inspection robot target areas requiring more detailed inspection. The robot guidance may be aided by way of an additional signal transmitted by the agent to the robot indicating that the object has been illuminated and attention switch may be required. Responsive to receiving the additional signal, the robot may initiate a search for the signal reflected by the illuminated area requiring its attention. Responsive to detecting the illuminated object and receipt of the additional signal, the robot may develop an association between the two events and the inspection task. The light guided attention system may influence the robot learning for subsequent actions.

Abstract: Apparatus and methods for plasticity in a spiking neuron network. In one implementation, a plasticity mechanism is configured based on a similarity measure between neuron post-synaptic and pre-synaptic activity. The similarity measure may comprise a cross-correlogram between the output spike train and input spike train, determined over a plasticity window. Several correlograms, corresponding to individual input connections delivering pre-synaptic input, may be combined. The combination may comprise for example a weighted average. The averaged correlograms may be used to construct the long term potentiation component of the plasticity. The long term depression component of the plasticity may comprise e.g., a monotonic function based on a statistical parameter associated with the adaptively determined long term potentiation component.

Abstract: A robotic vehicle may be operated by a learning controller comprising a trainable convolutional network configured to determine control signal based on sensory input. An input network layer may be configured to transfer sensory input into a hidden layer data using a filter convolution operation. Input layer may be configured to transfer sensory input into hidden layer data using a filter convolution. Output layer may convert hidden layer data to a predicted output using data segmentation and a fully connected array of efficacies. During training, efficacy of network connections may be adapted using a measure determined based on a target output provided by a trainer and an output predicted by the network. A combination of the predicted and the target output may be provided to the vehicle to execute a task. The network adaptation may be configured using an error back propagation method. The network may comprise an input reconstruction.

Abstract: A control apparatus and methods using context-dependent difference learning for controlling e.g., a plant. In one embodiment, the apparatus includes an actor module and a critic module. The actor module provides a control signal for the plant. The actor module is subject to adaptation, which is performed to optimize control strategy of the actor. The adaptation is based upon the reinforcement signal provided by the critic module. The reinforcement signal is calculated based on the comparison of a present control performance signal observed for a certain context signal, with a control performance signal observed for the same context in the past.

Abstract: Robotic devices may be operated by users remotely. A learning controller apparatus may detect remote transmissions comprising user control instructions. The learning apparatus may receive sensory input conveying information about robot's state and environment (context). The learning apparatus may monitor one or more wavelength (infrared light, radio channel) and detect transmissions from user remote control device to the robot during its operation by the user. The learning apparatus may be configured to develop associations between the detected user remote control instructions and actions of the robot for given context. When a given sensory context occurs, the learning controller may automatically provide control instructions to the robot that may be associates with the given context. The provision of control instructions to the robot by the learning controller may obviate the need for user remote control of the robot thereby enabling autonomous operation by the robot.

Abstract: Robotic devices may be operated by users remotely. A learning controller apparatus may detect remote transmissions comprising user control instructions. The learning apparatus may receive sensory input conveying information about robot's state and environment (context). The learning apparatus may monitor one or more wavelength (infrared light, radio channel) and detect transmissions from user remote control device to the robot during its operation by the user. The learning apparatus may be configured to develop associations between the detected user remote control instructions and actions of the robot for given context. When a given sensory context occurs, the learning controller may automatically provide control instructions to the robot that may be associates with the given context. The provision of control instructions to the robot by the learning controller may obviate the need for user remote control of the robot thereby enabling autonomous operation by the robot.

Abstract: Robotic devices may be operated by users remotely. A learning controller apparatus may detect remote transmissions comprising user control instructions. The learning apparatus may receive sensory input conveying information about robot's state and environment (context). The learning apparatus may monitor one or more wavelength (infrared light, radio channel) and detect transmissions from user remote control device to the robot during its operation by the user. The learning apparatus may be configured to develop associations between the detected user remote control instructions and actions of the robot for given context. When a given sensory context occurs, the learning controller may automatically provide control instructions to the robot that may be associates with the given context. The provision of control instructions to the robot by the learning controller may obviate the need for user remote control of the robot thereby enabling autonomous operation by the robot.