Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. A method includes: maintaining a plurality of training sessions; assigning, to each worker of one or more workers, a respective training session of the plurality of training sessions; repeatedly performing operations until meeting one or more termination criteria, the operations comprising: receiving an updated training session from a respective worker of the one or more workers, selecting a second training session, selecting, based on comparing the updated training session and the second training session using a fitness evaluation function, either the updated training session or the second training session as a parent training session, generating a child training session from the selected parent training session, and assigning the child training session to an available worker, and selecting a candidate model to be a trained model for the machine learning model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing representations of EEG measurements. One of the methods includes obtaining a plurality of EEG signal measurements corresponding to respective EEG trials of a user; generating a time-domain representation from the plurality of EEG signal measurements, where the time-domain representation includes a plurality of rows, and where each row corresponds to a different set of one or more EEG signal measurements; applying the time-domain representation as input to a neural network having a plurality of network parameters, final values of the network parameters having been determined by a transfer learning process where the neural network is initially trained to perform an image processing task and the neural network is subsequently trained to perform EEG analysis; and obtaining, from the neural network, a mental health prediction for the user.

Abstract: Systems and processes described herein can expand a limited data set of EEG trials into a larger data set by resampling subsets of EEG trial data. Implementations may employ one or more of a variety of different resampling techniques. For example, a subset of the available training data is selected to form a new set of training data. The subset can be selected using replacement (e.g., a sample can be selected more than once, and thus represented multiple times in the new set of training data). Alternatively the subset can be selected without using replacement (e.g., each sample is able to be selected only once, and thus represented a maximum of one time in the new set of training data).

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, from one or more electrodes, electroencephalographic (EEG) signals from a user; generating signal vectors from the EEG signals, each signal vector representing one channel of EEG signals. The actions include providing the signal vectors as input data to a variational autoencoder (VAE), wherein the VAE generates a latent representation of the input data, the latent representation having lower dimensionality than the signal vectors, and reconstructs the latent representation into an event related potential (ERP) of the corresponding EEG signal. The actions include providing, for display to a user, a graphical representation of the ERPs.

Abstract: A machine learning system for aggregating electroencephalographic (EEG) data in preparation for downstream analysis via further machine learning models. Machine learning models can be used to assist in diagnosis of various mental health conditions, brain-computer interface, mood detection systems, or other biometric functions. Implementations of the present disclosure, employ a portion of the transformer network (the attention encoder stack) to aggregate EEG trials or EEG data segments, in a data-driven way, by ensuring the important content of each trial is not lost. Each EEG trial to be aggregated is converted into an input embedding, or a vector which numerically represents the data in the trial.

Abstract: A machine learning system for aggregating electroencephalographic (EEG) data, as well as external data, in preparation for downstream analysis via further machine learning models. Machine learning models can be used to assist in diagnosis of various mental health conditions, brain-computer interface, mood detection systems, or other biometric functions. Implementations of the present disclosure, employ a portion of the transformer network (the attention encoder stack) to aggregate EEG trials or EEG data segments, in a data-driven way, by ensuring the important content of each trial is not lost. Each EEG trial to be aggregated is converted into an input embedding, or a vector which numerically represents the data in the trial.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating embeddings of EEG measurements. One of the methods includes obtaining a two-dimensional time-frequency electroencephalogram (EEG) representation corresponding to one or more EEG signal measurements of a user; processing the time-frequency EEG representation using a first neural network having a plurality of first network parameters to generate an embedding of the time-frequency EEG representation, wherein the first neural network has been trained using transfer learning; and providing the embedding of the time-frequency EEG representation to a downstream neural network to generate a mental health prediction for the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating embeddings of EEG measurements. One of the methods includes obtaining a plurality of electroencephalogram (EEG) signal measurements of a user, wherein each EEG signal measurement corresponds to one of a plurality of prompt types of an EEG task; generating, from the plurality of EEG signal measurements, a plurality of network inputs each corresponding to a different prompt type of the plurality of prompt types of the EEG task; processing the network inputs using a twin neural network to generate respective network outputs each corresponding to a different prompt type of the plurality of prompt types of the EEG task; and providing the network outputs to a downstream neural network to generate a mental health prediction for the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an auto-encoder to de-noise task specific electroencephalogram (EEG) signals. One of the methods includes training a variational auto-encoder (VAE) including to learn a plurality of parameter values of the VAE by applying, as first training input to the VAE, training data, the training data comprising electroencephalogram (EEG) data representing brain activities of individual persons when performing different tasks; and after the training, adapting the VAE for a specific task by applying, as second training input to the VAE, adaptation data, the adaptation data comprising task-specific EEG data representing brain activities of individual persons when performing the specific task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining psychological data, generating a psychopathological analysis data structure (PADS), applying a latent factor analysis algorithm to the PADS to obtain a psychopathological latent factor space (PLFS), generating a latent factor graph, and outputting the latent factor graph.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving physiological data of a patient, obtaining ecological momentary assessment (EMA) data by sending an EMA data prompt, and receiving patient input responsive to the EMA data prompt; and generating, based on the EMA data and the physiological data, a graphical representation of the patient's idiomatic psychopathology symptom network as a symptom network graph.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. A method includes: maintaining a plurality of training sessions; assigning, to each worker of one or more workers, a respective training session of the plurality of training sessions; repeatedly performing operations until meeting one or more termination criteria, the operations comprising: receiving an updated training session from a respective worker of the one or more workers, selecting a second training session, selecting, based on comparing the updated training session and the second training session using a fitness evaluation function, either the updated training session or the second training session as a parent training session, generating a child training session from the selected parent training session, and assigning the child training session to an available worker, and selecting a candidate model to be a trained model for the machine learning model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for causing a stimulus presentation system to present first content to a patient. Obtaining, from a brainwave sensor, electroencephalography (EEG) signals of the patient while the first content is being presented to the patient. Identifying, from within the EEG signals of the patient, first brainwave signals associated with a first brain system of the patient, the first brainwave signals representing a response by the patient to the first content. Determining, based on providing the first brainwave signals as input features to a machine learning model, a likelihood that the patient will experience a type of depression within a period of time. Providing, for display on a user computing device, data indicating the likelihood that the patient will experience the type of depression within the period of time.

Abstract: Provided is a method of improving plant embryo development and/or germination. The method comprises developing plant embryos in the presence of nitric oxide (NO). The method entails the step of incubating plant embryogenic suspensor mass (ESM) in, or on, a development medium containing a nitric oxide donor for a period of time to develop mature somatic embryos. The method disclosed herein improves the yield and/or the germination frequency of plant embryos as compared to plant embryos developed by conventional methods without a nitric oxide donor in the medium.

Abstract: Systems, methods and devices for using ephemeris data in GNSS receivers and systems are provided. Receivers using synthetic ephemeris data for longer ephemeris availability under poor reception conditions are updated using a variety of techniques that allow for the transfer of accurate information onto degraded synthetic ephemeris information.

Abstract: Systems, methods and devices for using ephemeris data in GNSS receivers and systems are provided. Receivers using synthetic ephemeris data for longer ephemeris availability under poor reception conditions are updated using a variety of techniques that allow for the transfer of accurate information onto degraded synthetic ephemeris information.

Abstract: Systems, methods and devices for using ephemeris data in GNSS receivers and systems are provided. Receivers using synthetic ephemeris data for longer ephemeris availability under poor reception conditions are updated using a variety of techniques that allow for the transfer of accurate information onto degraded synthetic ephemeris information.

Abstract: According to one embodiment of the present invention, a method for debugging a computer system is provided. According to one embodiment of the invention, a method includes encrypting data and query program instructions using correlated order invariant encrypting, the data and query program instructions operating in a customer computer system. The encrypted data and encrypted query program instructions are then transferred to a servicing entity having a test system. The encrypted data and encrypted query program instructions are run on the test system to generate a set of results. The set of results are then used to generate a diagnosis of a problem with the customer computer system. Thus the customer problem can be resolved without the servicing entity having access to the customer's data and query program instructions.

Abstract: A computer-implemented method for managing maintenance of a computer program can include the steps of receiving usage data from a plurality of users of the computer program, wherein the usage data identifies at least one portion of the computer program accessed by one of the users, and for each portion of the computer program, determining a usage according to the received usage data and assigning a priority level according to the determined usage, where the priority level indicates a relative priority of the portion compared to other portions in the computer program.

Abstract: A method for treating gastric acid disorders with a non-enteric coated proton pump inhibitor in a pharmaceutically acceptable carrier including a bicarbonate salt of a Group IA metal and a carbonate salt of a Group IA metal; and a pharmaceutical composition of a non-enteric coated proton pump inhibitor in a pharmaceutically acceptable carrier including a bicarbonate salt of a Group IA metal and a carbonate salt of a Group IA metal are disclosed. A presently preferred proton pump inhibitor is lansoprazole, a presently preferred bicarbonate salt is sodium bicarbonate, and a presently preferred carbonate salt is sodium carbonate. The composition is a fast-acting formulation which reduces the undesirable belching associated with proton pump inhibitor formulations that contain high doses of sodium bicarbonate.