Abstract: An autonomous vehicle, system and method of operating the autonomous vehicle. The system includes an episodic memory, a hyper-association module and a navigation system. The episodic memory stores a plurality of episodes, recalls a plurality of candidate episodes in response to receiving a partial prefix and recalls a hypothesis episode in response to receiving an intermediate episode. The hyper-association module receives the plurality of candidate episodes from the episodic memory and obtains the intermediate episode from the plurality of candidate episodes. The navigation system navigates the autonomous vehicle using the hypothesis episode.

Abstract: Described is a system for online vehicle recognition in an autonomous driving environment. Using a learning network comprising an unsupervised learning component and a supervised learning component, images of moving vehicles extracted from videos captured in the autonomous driving environment are learned and classified. Vehicle feature data is extracted from input moving vehicle images. The extracted vehicle feature data is clustered into different vehicle classes using the unsupervised learning component. Vehicle class labels for the different vehicle classes are generated using the supervised learning component. Based on a vehicle class label for a moving vehicle in the autonomous driving environment, the system selects an action to be performed by the autonomous vehicle, and causes the selected action to be performed by the autonomous vehicle in the autonomous driving environment.

Abstract: A system configured to identify a target in a synthetic aperture radar signal includes: a feature extractor configured to extract a plurality of features from the synthetic aperture radar signal; an input spiking neural network configured to encode the features as a first plurality of spiking signals; a multi-layer recurrent neural network configured to compute a second plurality of spiking signals based on the first plurality of spiking signals; a readout neural layer configured to compute a signal identifier based on the second plurality of spiking signals; and an output configured to output the signal identifier, the signal identifier identifying the target.

Abstract: Described is a system for an episodic memory used by an automated platform. The system acquires data from an episodic memory that comprises an event database, an event-sequence graph, and an episode list. Using the event-sequence graph, the system identifies a closest node to a current environment for the automated platform. Based on the closest node and using a hash function or key based on the hash function, the system retrieves from the event database an episode that corresponds to the closest node, the episode including a sequence of events. Behavior of the automated platform in the current environment is guided based on the data from the episodic memory.

Abstract: An autonomous vehicle, system and method of operating the autonomous vehicle. The system includes an episodic memory, a hyper-association module and a navigation system. The episodic memory stores a plurality of episodes, recalls a plurality of candidate episodes in response to receiving a partial prefix and recalls a hypothesis episode in response to receiving an intermediate episode. The hyper-association module receives the plurality of candidate episodes from the episodic memory and obtains the intermediate episode from the plurality of candidate episodes. The navigation system navigates the autonomous vehicle using the hypothesis episode.

Abstract: Described is a system for decoding spiking reservoirs even when the spiking reservoir has continuous synaptic plasticity. The system uses a set of training patterns to train a neural network having a spiking reservoir comprised of spiking neurons. A test pattern duration d is estimated for a set of test patterns P, and each test pattern is presented to the spiking reservoir for a duration of d/P seconds. Output spikes from the spiking reservoir are generated via readout neurons. The output spikes are measured and the measurements are used to compute firing rate codes, each firing rate code corresponding to a test pattern in the set of test patterns P. The firing rate codes are used to decode performance of the neural network by computing a discriminability index (DI) to discriminate between test patterns in the set of test patterns P.

Abstract: Described is a system for online vehicle recognition in an autonomous driving environment. Using a learning network comprising an unsupervised learning component and a supervised learning component, images of moving vehicles extracted from videos captured in the autonomous driving environment are learned and classified. Vehicle feature data is extracted from input moving vehicle images. The extracted vehicle feature data is clustered into different vehicle classes using the unsupervised learning component. Vehicle class labels for the different vehicle classes are generated using the supervised learning component. Based on a vehicle class label for a moving vehicle in the autonomous driving environment, the system selects an action to be performed by the autonomous vehicle, and causes the selected action to be performed by the autonomous vehicle in the autonomous driving environment.

Abstract: A system and method is taught for data processing in an autonomous vehicle control system. Using information is acquired from the vehicle, network interface, and sensors mounted on the vehicle, the system can perceive situations around it with much less complexity in computation without losing crucial details, and then make navigation and control decisions. The system and method are operative to generate situation aware events, store them, and recall to predict situations for autonomous driving.

Abstract: A system and method is taught for data processing in an autonomous vehicle control system. Using information is acquired from the vehicle, network interface, and sensors mounted on the vehicle, the system can perceive situations around it with much less complexity in computation without losing crucial details, and then make navigation and control decisions. The system and method are operative to generate situation aware events, store them, and recall to predict situations for autonomous driving.

Abstract: A system and method is taught for data processing where an environment around the self-vehicle is encoded into ego centric and geocentric overlapping coordinate systems. The overlapping coordinate systems are then divided into adaptively sized grid cells according to characteristics of environments and the self-vehicle status. Each grid cell is defined with one of representative event patterns and risk values to the self-vehicle. The autonomous driving system is then operative to provide a real time assessment of the surrounding environment in response to the grid cell data. And temporal sequences of the grid cell data are stored in the episodic memory and recalled from it during driving.

Abstract: Described is a system for an episodic memory used by an automated platform. The system acquires data from an episodic memory that comprises an event database, an event-sequence graph, and an episode list. Using the event-sequence graph, the system identifies a closest node to a current environment for the automated platform. Based on the closest node and using a hash function or key based on the hash function, the system retrieves from the event database an episode that corresponds to the closest node, the episode including a sequence of events. Behavior of the automated platform in the current environment is guided based on the data from the episodic memory.

Abstract: Described is a system for decoding spiking reservoirs even when the spiking reservoir has continuous synaptic plasticity. The system uses a set of training patterns to train a neural network having a spiking reservoir comprised of spiking neurons. A test pattern duration d is estimated for a set of test patterns P, and each test pattern is presented to the spiking reservoir for a duration of d/P seconds. Output spikes from the spiking reservoir are generated via readout neurons. The output spikes are measured and the measurements are used to compute firing rate codes, each firing rate code corresponding to a test pattern in the set of test patterns P. The firing rate codes are used to decode performance of the neural network by computing a discriminability index (DI) to discriminate between test patterns in the set of test patterns P.

Abstract: A synaptic time-multiplexed (STM) neuromorphic network includes a neural fabric that includes nodes and switches to define inter-nodal connections between selected nodes of the neural fabric. The STM neuromorphic network further includes a neuromorphic controller to form subsets of a set of the inter-nodal connections representing a fully connected neural network. Each subset is formed during a different time slot of a plurality of time slots of a time multiplexing cycle of the STM neuromorphic network. In combination, the inter-nodal connection subsets implement the fully connected neural network. A method of synaptic time multiplexing a neuromorphic network includes providing the neural fabric and forming the subsets of the set of inter-nodal connections.

Abstract: A neural network, wherein a portion of the neural network comprises: a first array having a first number of neurons, wherein the dendrite of each neuron of the first array is provided for receiving an input signal indicating that a measured parameter gets closer to a predetermined value assigned to said neuron; and a second array having a second number of neurons, wherein the second number is smaller than the first number, the dendrite of each neuron of the second array forming an excitatory STDP synapse with the axon of a plurality of neurons of the first array; the dendrite of each neuron of the second array forming an excitatory STDP synapse with the axon of neighboring neurons of the second array.

Abstract: A synaptic time-multiplexed (STM) neuromorphic network includes a neural fabric that includes nodes and switches to define inter-nodal connections between selected nodes of the neural fabric. The STM neuromorphic network further includes a neuromorphic controller to form subsets of a set of the inter-nodal connections representing a fully connected neural network. Each subset is formed during a different time slot of a plurality of time slots of a time multiplexing cycle of the STM neuromorphic network. In combination, the inter-nodal connection subsets implement the fully connected neural network. A method of synaptic time multiplexing a neuromorphic network includes providing the neural fabric and forming the subsets of the set of inter-nodal connections.

Abstract: A neural network, wherein a portion of the neural network comprises: a first array having a first number of neurons, wherein the dendrite of each neuron of the first array is provided for receiving an input signal indicating that a measured parameter gets closer to a predetermined value assigned to said neuron; and a second array having a second number of neurons, wherein the second number is smaller than the first number, the dendrite of each neuron of the second array forming an excitatory STDP synapse with the axon of a plurality of neurons of the first array; the dendrite of each neuron of the second array forming an excitatory STDP synapse with the axon of neighboring neurons of the second array.

Abstract: A method and system for characterizing, detecting, and predicting or forecasting multiple target events from a past history of these events includes compressing temporal data streams into self-organizing map (SOM) clusters, and determining trajectories of the temporal streams via the clusters to predict the multiple target events. The system includes an evolutionary multi-objective optimization (EMO) module for processing the temporal data streams, which are obtained from a plurality of heterogeneous domains; a SOM module for characterizing the temporal data streams into self-organizing map clusters; and a target event prediction (TEP) module for generating prediction models of the map clusters. The SOM module employs a vector quantization method that places a set of vectors on a low-dimensional grid in an ordered fashion. The prediction models each include trajectories of the temporal data streams, and the system predicts the multiple target events using the trajectories.

Abstract: Described is a fault-tolerant electro-mechanical system that is able to saccade to a target by training and using a signal processing technique. The invention enables tracking systems, such as next generational cameras, to be developed for autonomous platforms and surveillance systems where environment conditions are unpredictable. The invention includes at least one sensor configured to relay a signal containing positional information of a stimulus. At least one actuator is configured to manipulate the sensor to enable the sensor to track the stimulus. A processing device is configured to receive positional information from each sensor and each actuator. The processing device sends a positional changing signal to at least one actuator and adjusts at least one positional changing signal according to the information from each sensor and each actuator to enable the actuator to cause the sensor to track the stimulus.

Abstract: A method and system for characterizing, detecting, and predicting or forecasting multiple target events from a past history of these events includes compressing temporal data streams into self-organizing map (SOM) clusters, and determining trajectories of the temporal streams via the clusters to predict the multiple target events. The system includes an evolutionary multi-objective optimization (EMO) module for processing the temporal data streams, which are obtained from a plurality of heterogeneous domains; a SOM module for characterizing the temporal data streams into self-organizing map clusters; and a target event prediction (TEP) module for generating prediction models of the map clusters. The SOM module employs a vector quantization method that places a set of vectors on a low-dimensional grid in an ordered fashion. The prediction models each include trajectories of the temporal data streams, and the system predicts the multiple target events using the trajectories.

Abstract: Disclosed herein are a system and method for trend prediction of signals in a time series using a Markov model. The method includes receiving a plurality of data series and input parameters, where the input parameters include a time step parameter, preprocessing the plurality of data series according to the input parameters, to form binned and classified data series, and processing the binned and classified data series. The processing includes initializing a Markov model for trend prediction, and training the Markov model for trend prediction of the binned and classified data series to form a trained Markov model. The method further includes deploying the trained Markov model for trend prediction, including outputting trend predictions. The method develops an architecture for the Markov model from the data series and the input parameters, and disposes the Markov model, having the architecture, for trend prediction.