Abstract: Systems and methods for a machine learning system to learn a new skill without catastrophically forgetting an existing skill and to continually learn in a self-supervised manner during operation, without human intervention.

Abstract: A brain machine interface system for use with an electroencephalogram to identify a behavioral intent of a person is disclosed. The system includes an electroencephalogram configured to sense electromagnetic signals generated by a brain of a person. The electromagnetic signals include a time component and a frequency component. A monitor monitors a response of the person to a stimulus and a characteristic of the stimulus. A synchronization module synchronizes the sensed electromagnetic signals with the response and the characteristic to determine a set of electromagnetic signals corresponding to the monitored response and the characteristic. A processor processes the set of electromagnetic signals and extracts feature vectors. The feature vectors define a class of behavioral intent. The processor determines the behavioral intent of the person based on the feature vectors. A brain machine interface and a method for identifying a behavioral intent of a person is also disclosed.

Abstract: A vision-cued random-access LIDAR system and method which determines the location and/or navigation path of a moving platform. A vision system on a moving platform identifies a region of interest. The system classifies objects within the region of interest, and directs random-access LIDAR to ping one or more of the classified objects. The platform is located in three dimensions using data from the vision system and LIDAR. The steps of classifying, directing, and locating are preferably performed continuously while the platform is moving and/or the vision system's field-of-view (FOV) is changing. Objects are preferably classified using at least one smart-vision algorithm, such as a machine-learning algorithm.

Abstract: A vision-cued random-access LIDAR system and method which determines the location and/or navigation path of a moving platform. A vision system on a moving platform identifies a region of interest. The system classifies objects within the region of interest, and directs random-access LIDAR to ping one or more of the classified objects. The platform is located in three dimensions using data from the vision system and LIDAR. The steps of classifying, directing, and locating are preferably performed continuously while the platform is moving and/or the vision system's field-of-view (FOV) is changing. Objects are preferably classified using at least one smart-vision algorithm, such as a machine-learning algorithm.

Abstract: A brain machine interface system for use with an electroencephalogram to identify a behavioral intent of a person is disclosed. The system includes an electroencephalogram configured to sense electromagnetic signals generated by a brain of a person. The electromagnetic signals include a time component and a frequency component. A monitor monitors a response of the person to a stimulus and a characteristic of the stimulus. A synchronization module synchronizes the sensed electromagnetic signals with the response and the characteristic to determine a set of electromagnetic signals corresponding to the monitored response and the characteristic. A processor processes the set of electromagnetic signals and extracts feature vectors. The feature vectors define a class of behavioral intent. The processor determines the behavioral intent of the person based on the feature vectors. A brain machine interface and a method for identifying a behavioral intent of a person is also disclosed.

Abstract: A brain machine interface system for use with an electroencephalogram to identify a behavioral intent of a person is disclosed. The system includes an electroencephalogram configured to sense electromagnetic signals generated by a brain of a person. The electromagnetic signals include a time component and a frequency component. A monitor monitors a response of the person to a stimulus and a characteristic of the stimulus. A synchronization module synchronizes the sensed electromagnetic signals with the response and the characteristic to determine a set of electromagnetic signals corresponding to the monitored response and the characteristic. A processor processes the set of electromagnetic signals and extracts feature vectors. The feature vectors define a class of behavioral intent. The processor determines the behavioral intent of the person based on the feature vectors. A brain machine interface and a method for identifying a behavioral intent of a person is also disclosed.

Abstract: Systems and methods for a machine learning system to learn a new skill without catastrophically forgetting an existing skill and to continually learn in a self-supervised manner during operation, without human intervention.

Abstract: Provided is an apparatus, system, and method for targeted memory enhancement. A computer processing circuit receives a plurality of electroencephalography (EEG) signals from a plurality of spatially separated EEG sensors located on the head of a subject that is asleep. A first process of the computer processing system determines a sleep state of the subject and upon determining that the subject is in sleep stage 2 or 3 based on a specific EEG signal, the processing system triggers a second process of the computer processing system that determines a transition event in the specific EEG signal, and upon detecting the transition event delivers an intervention to the subject designed to evoke a specific neurophysiological change to the subject.

Abstract: Provided is an apparatus, system, and method for targeted sleep enhancement. A computer processing circuit receives a plurality of EEG signals from a plurality of spatially separated EEG sensors configured to be located on the head of a subject. The computer processing circuit executes machine executable instructions to: receive and process the plurality of EEG signals; determine that the subject is in sleep stage 3 based on a specific EEG signal of the processed plurality of EEG signals; determine a period of at least one of quiescent and asynchronous brain activity of the subject, wherein the period is determined based on the processed plurality of EEG signals; and deliver a transcranial electrical stimulation through the plurality of stimulation electrodes during the period of quiescent brain activity.

Abstract: Provided is an apparatus, system, and method for targeted memory enhancement. A computer processing circuit receives a plurality of electroencephalography (EEG) signals from a plurality of spatially separated EEG sensors located on the head of a subject that is asleep. A first process of the computer processing system determines a sleep state of the subject and upon determining that the subject is in sleep stage 2 or 3 based on a specific EEG signal, the processing system triggers a second process of the computer processing system that determines a transition event in the specific EEG signal, and upon detecting the transition event delivers an intervention to the subject designed to evoke a specific neurophysiological change to the subject.

Abstract: A brain machine interface system for use with an electroencephalogram to identify a behavioral intent of a person is disclosed. The system includes an electroencephalogram configured to sense electromagnetic signals generated by a brain of a person. The electromagnetic signals include a time component and a frequency component. A monitor monitors a response of the person to a stimulus and a characteristic of the stimulus. A synchronization module synchronizes the sensed electromagnetic signals with the response and the characteristic to determine a set of electromagnetic signals corresponding to the monitored response and the characteristic. A processor processes the set of electromagnetic signals and extracts feature vectors. The feature vectors define a class of behavioral intent. The processor determines the behavioral intent of the person based on the feature vectors. A brain machine interface and a method for identifying a behavioral intent of a person is also disclosed.

Abstract: EEG-based acceleration of second language learning is accomplished by measuring via single-trial EEG a learner's cognitive response to the presentation (visual or auditory) of language learning materials and updating a user model of latent traits related to language-learning skills in accordance with the cognitive response. The user model is suitably updated with each trial, each trial being triggered by learner fixation on a portion of visual materials and/or a next phoneme in auditory materials. Additional discrimination may be achieved through the use of saccades or fixation duration features.

Abstract: Cognitive biometrics comprises augmenting the richness of biometric signatures that can be extracted from mouse dynamics by introducing perturbations in the response of the computer mouse and measuring the motor responses of the individual user. User responses to unexpected and subtle perturbations (e.g., small changes in mouse velocity, position and/or acceleration) reveal new unique sources of information in the mouse movement signal that reflect the user's cognitive strategies and are inaccessible via existing mouse biometric technologies. A user's response to these perturbations contains information about intrinsic cognitive qualities that can be used as a robust biometric for personal authentication and to support profiling of the individual (e.g., gender, cultural background, cognitive or emotional state, cognitive quality etc.).

Abstract: A computer vision system provides a universal scene descriptor (USD) framework and methodology for using the USD framework to extract multi-level semantic metadata from scenes. The computer vision system adopts the human vision system principles of saliency, hierarchical feature extraction and hierarchical classification to systematically extract scene information at multiple semantic levels.

Abstract: Fixation-locked measurement of brain activity generates time-coded cues indicative of whether an operator exhibited a significant cognitive response to task-relevant stimuli. The free-viewing environment is one in which the presentation of stimuli is natural to the task encompassing both pre- and post-fixation stimuli and the operator is allowed to move his or her eyes naturally to perform the task.

Abstract: The human neural response is coupled with computer pattern analysis for robust single-event detection of significant non-stationary brain responses triggered upon occurrence of a task-relevant stimulus. Classifier performance is enhanced fusing together the outputs of multiple different classifiers albeit multiple spatial classifiers to extract a temporal pattern as the brain response evolves, time and frequency-based spatio-temporal classifiers, and/or EEG and pupillary classifiers.

Abstract: The human neural response is coupled with computer pattern analysis for robust single-event detection of significant non-stationary brain responses triggered upon occurrence of a task-relevant stimulus. Classifier performance is enhanced fusing together the outputs of multiple different classifiers albeit multiple spatial classifiers to extract a temporal pattern as the brain response evolves, time and frequency-based spatio-temporal classifiers, and/or EEG and pupillary classifiers.

Abstract: Bayesian super-resolution techniques fuse multiple low resolution images (possibly from multiple bands) to infer a higher resolution image. The super-resolution and fusion concepts are portable to a wide variety of sensors and environmental models. The procedure is model-based inference of super-resolved information. In this approach, both the point spread function of the sub-sampling process and the multi-frame registration parameters are optimized simultaneously in order to infer an optimal estimate of the super-resolved imagery. The procedure involves a significant number of improvements, among them, more accurate likelihood estimates and a more accurate, efficient, and stable optimization procedure.

Abstract: A computer vision system provides a universal scene descriptor (USD) framework and methodology for using the USD framework to extract multi-level semantic metadata from scenes. The computer vision system adopts the human vision system principles of saliency, hierarchical feature extraction and hierarchical classification to systematically extract scene information at multiple semantic levels.

Abstract: EEG-based acceleration of second language learning is accomplished by measuring via single-trial EEG a learner's cognitive response to the presentation (visual or auditory) of language learning materials and updating a user model of latent traits related to language-learning skills in accordance with the cognitive response. The user model is suitably updated with each trial, each trial being triggered by learner fixation on a portion of visual materials and/or a next phoneme in auditory materials. Additional discrimination may be achieved through the use of saccades or fixation duration features.