Abstract: Described is a system for improving generalization of an agent, such as an autonomous vehicle, to unanticipated environmental changes. A set of concepts from the agent's experiences of an environment are extracted and consolidated into an episodic world model. Using the episodic world model, a dream sequence of prospective simulations, based on a selected set of concepts and constrained by the environment's semantics and dynamics, is generated. The dream sequence is converted into a sensor data format, which is used for augmented training of the agent to operate in the environment with improved generalization to unanticipated changes in the environment.

Abstract: A method of predictive navigation control for an ego vehicle includes: comparing a cue node to each of a plurality of episodic memory nodes in an episodic memory structure, wherein the cue node represents a new event representing distances, speeds and headings of one or more newly observed objects about the ego vehicle, and wherein the episodic memory structure includes a network of nodes each representing a respective previously existing event and having a respective node risk and likelihood; determining which of the nodes has a smallest respective difference metric, thus defining a best matching node; consolidating the cue node with the best matching node if the smallest difference metric is less than a match tolerance, else adding a new node corresponding to the cue node to the episodic memory structure; and identifying a likeliest next node and/or a riskiest next node.

Abstract: Described is a system for competency assessment of an autonomous system. The system extracts semantic concepts representing a situation. Actions taken by the autonomous system are associated with semantic concepts that are activated when the actions are taken in the situation. The system measures an outcome of the actions taken in the situation and generates a reward metric. The semantic concepts representing the situation are stored as a memory with the actions taken in the situation and the reward metric as a memory. A prospective simulation is generated based on recall of the memory. A competency metric and an experience metric are determined. Competent operational control of the autonomous system is maintained when at least one of the competency metric and the experience metric is above a minimum value. An alert is generated when at least one of the competency metric and the experience metric falls below the minimum value.

Abstract: A method of predictive navigation control for an ego vehicle includes: comparing a cue node to each of a plurality of episodic memory nodes in an episodic memory structure, wherein the cue node represents a new event representing distances, speeds and headings of one or more newly observed objects about the ego vehicle, and wherein the episodic memory structure includes a network of nodes each representing a respective previously existing event and having a respective node risk and likelihood; determining which of the nodes has a smallest respective difference metric, thus defining a best matching node; consolidating the cue node with the best matching node if the smallest difference metric is less than a match tolerance, else adding a new node corresponding to the cue node to the episodic memory structure; and identifying a likeliest next node and/or a riskiest next node.

Abstract: In an embodiment of the present invention, a method for generating a prediction of ability of a subject to perform a task in a future time step includes receiving performance data corresponding to a performance of the subject on the task; receiving a plurality of biometric inputs computed based on physiological data during the performance of the subject on the task; identifying a numerical relationship between the performance data and the plurality of biometric inputs; generating a modulation parameter for each of the plurality of biometric inputs based on the identified numerical relationship; loading a plurality of state variable inputs produced by a generic model of performance; and generate the prediction of ability to perform the task at the prediction time, generated by a trained performance predictor based on biometric inputs predicted based on the modulation parameters.

Abstract: Described is a system for cueing a specific memory in a waking state. The system sends an initiation signal to a memory recall controller to select a stored stimulation pattern previously associated with a specific memory of an event. The system signals to a memory recall controller to initiate delivery of the selected stimulation pattern to a brain in a waking state for a duration of the event via a brain stimulation system. Following completion of the event, the system signals for the memory recall controller to stop the brain stimulation system from delivering the selected stimulation pattern.

Abstract: An autonomous navigation system for a vehicle includes a controller configured to control the vehicle, sensors configured to detect objects in a path of the vehicle, nonvolatile memory including an artificial neural network configured to classify the objects detected by the sensors, and a processor. The artificial neural network includes a series of neurons in each of an input layer, at least one hidden layer, and an output layer. The memory includes instructions which, when executed by the processor, cause the processor to train the artificial neural network on a first task, identify, utilizing a contrastive excitation backpropagation algorithm, important neurons for the first task, identify, utilizing a learning algorithm, important synapses between the neurons for the first task based on the important neurons identified, and rigidify the important synapses to achieve selective plasticity of the series of neurons in the artificial neural network.

Abstract: A method for retraining an artificial neural network trained on data from an old task includes training the artificial neural network on data from a new task different than the old task, calculating a drift, utilizing Sliced Wasserstein Distance, in activation distributions of a series of hidden layer nodes during the training of the artificial neural network with the new task, calculating a number of additional nodes to add to at least one hidden layer based on the drift in the activation distributions, resetting connection weights between input layer nodes, hidden layer nodes, and output layer nodes to values before the training of the artificial neural network on the data from the new task, adding the additional nodes to the at least one hidden layer, and training the artificial neural network on data from the new task.

Abstract: Described is a system for weakening an undesirable memory. The system initiates application of a first pattern of spatiotemporally distributed transcranial stimulation via a set of electrodes to a subject who is in a calm mental state, causing association of the first pattern of spatiotemporally distributed transcranial stimulation with the calm mental state. The system then initiates application of the first pattern of spatiotemporally distributed transcranial stimulation via the set of electrodes when the undesirable memory is recalled by the subject, causing recall of the calm mental state and reconsolidation of the undesirable memory with the calm mental state.

Abstract: A brain-machine interface system configured to decode neural signals to control a target device includes a sensor to sample the neural signals, and a computer-readable storage medium having software instructions, which, when executed by a processor, cause the processor to transform the neural signals into a common representational space stored in the system, provide the common representational space as a state representation to inform an Actor recurrent neural network policy of the system, generate and evaluate, utilizing a deep recurrent neural network of the system having a generative sequence decoder, predictive sequences of control signals, supply a control signal to the target device to achieve an output of the target device, determine an intrinsic biometric-based reward signal, from the common representational space, based on an expectation of the output of the target device, and supply the intrinsic biometric-based reward signal to a Critic model of the system.

Abstract: Described is a system for selecting among intelligence elements of a neural model. An intelligence element is selected from a set of intelligence elements which change group attack probability estimates and processed via multiple operations. A semantic memory component learns group probability distributions and rules based on the group probability distributions. The rules determine which intelligence element related to the groups to select. Given an environment of new probability distributions, the semantic memory component recalls which rule to select to receive a particular intelligence element. An episodic memory component recalls a utility value for each information element A procedural memory component recalls and selects the information element considered to have the highest utility. A list of intelligence elements is published to disambiguate likely attackers.

Abstract: Described is a system for competency assessment of an autonomous system. The system extracts semantic concepts representing a situation. Actions taken by the autonomous system are associated with semantic concepts that are activated when the actions are taken in the situation. The system measures an outcome of the actions taken in the situation and generates a reward metric. The semantic concepts representing the situation are stored as a memory with the actions taken in the situation and the reward metric as a memory. A prospective simulation is generated based on recall of the memory. A competency metric and an experience metric are determined. Competent operational control of the autonomous system is maintained when at least one of the competency metric and the experience metric is above a minimum value. An alert is generated when at least one of the competency metric and the experience metric falls below the minimum value.

Abstract: A brain-machine interface system configured to decode neural signals to control a target device includes a sensor to sample the neural signals, and a computer-readable storage medium having software instructions, which, when executed by a processor, cause the processor to transform the neural signals into a common representational space stored in the system, provide the common representational space as a state representation to inform an Actor recurrent neural network policy of the system, generate and evaluate, utilizing a deep recurrent neural network of the system having a generative sequence decoder, predictive sequences of control signals, supply a control signal to the target device to achieve an output of the target device, determine an intrinsic biometric-based reward signal, from the common representational space, based on an expectation of the output of the target device, and supply the intrinsic biometric-based reward signal to a Critic model of the system.

Abstract: Described is a system for biofeedback, the system including one or more processors and a memory, the memory being a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions, the one or more processors perform operations including using a first biometric sensor during performance of a current task, acquiring first biometric data, and producing a first biometric value by assessing the first biometric data. The one or more processors further perform operations including determining a first relevance based on a first significance of a first correlation between the first biometric value and the current task, and controlling a device based on the first relevance and the first biometric value.

Abstract: A system for closed-loop pulsed transcranial stimulation for cognitive enhancement. During operation, the system identifies a region of interest (ROI) in a subject's brain and then estimates ROI source activations based on the estimated source of the ROI. It is then determined if a subject is in a bad encoding state based on the ROI source activations. Finally, one or more electrodes are activated to apply a pulsed transcranial stimulation (tPS) therapy when the subject is in a bad encoding state, a predefined external event or behavior occurs, or the subject is in a consolidation state during sleep.

Abstract: Described is a closed-loop intervention control system for memory consolidation in a subject. During operation, the system simulates memory changes of a first memory in a subject during waking encoding of the memory, and then while the subject is sleeping and coupled to an intervention system. Based on the simulated memory changes, the system predicts behavioral performance for the first memory, the behavioral performance being a probability that the first memory can be recalled on cue. The system can be used to control operation (e.g., turn on or off) of the intervention system with respect to the first memory based on the behavioral performance of the first memory determined by the simulation.

Abstract: Described is a system for treating traumatic memories. During a wake stage, a virtual environment is displayed to a subject. A traumatic episode that may be similar to a traumatic memory of the subject is displayed to the user in the virtual environment in a benign setting. A transcranial current stimulation (tCS) controller applies a pattern of transcranial direct current stimulation (tDCS) to the subject during the traumatic episode, such that the traumatic memory in a benign setting is associated with the pattern of tDCS. During a sleep stage, if slow-wave sleep in the subject is detected via electroencephalogram (EEG) recordings, then in a first time period, the tCS controller may a transcranial alternating current stimulation (tACS) to the subject followed by a second time period without stimulation. In a third time period, the tCS controller may apply the pattern of tDCS to the subject. The sleep stage may be repeated until a desired weakening of the traumatic memory is reached.

Abstract: Described is a system for memory improvement intervention. Based on both real-time EEG data and a neural model, the system simulates replay of a person's specific memory during a sleep state. Using the neural model, a prediction of behavioral performance of the replay of the specific memory is generated. If the prediction is below a first threshold, then using a memory enhancement intervention system, the system applies an intervention during the sleep state to improve consolidation of the specific memory. If the prediction is below a second threshold, the system reduces the intervention performed using the memory enhancement intervention system.

Abstract: Described is a closed-loop control system for memory consolidation in a subject. During operation, the system encodes information regarding environmental items as memories in both a long-term memory store and a short-term memory store. The system generates an activation level representation of a memory of interest related to at least one of the environmental items. An association strength representation for the memories is also generated. Memory consolidation is simulated when the subject is in NREM sleep or quiet waking by strengthening the association strength representation related to the memory of interest. The system predicts behavioral performance for the memory of interest as a probability that the memory of interest can be recalled on cue. When the behavioral performance is below a threshold, an intervention system can be activated.

Abstract: Described is a system for storing and retrieving a memory in context. A memory formed for a given context is encoded in a neural model of the entorhinal-hippocampal system, forming a context-appropriate memory. The context-appropriate memory is comprised of an association between presented environmental cues and presence of a rewarded event. The system is able to discriminate between environmental cues in an environment surrounding a vehicle and retrieve at least one encoded context-appropriate memory. Using the at least one retrieved encoded context-appropriate memory, the system determines whether to initiate a collision avoidance operation to cause the vehicle to proactively avoid a collision.