Neumora Therapeutics, Inc.

Microsoft Technology Licensing, LLC

Instart Logic, Inc.

Blackthorn Therapeutics, Inc.

Blackthor Therapeutics, Ine.

Parvez Ahammad

Humberto Andres Gonzalez Cabezas

Yuelu Liu

Monika Sharma Mellem

William J Martin

Pablo Christian Gersberg

Matthew Edward Kollada

Ryan M Rogers

Qingzhu Gao

Rahul Tandra

Hariharan Kolam

Lin Xu

Min Liu

Brian Kennedy

Jing Wang

Subbu Subramaniam

Yu Liu

David Pardoe

Adrian Rivera Cardoso

Jefferson Lai

Ryan T Tecco

Man Chun D Leung

Yajun Wang

Jilei Yang

Fangfang Tan

Mark B Cesar

Yu Chen

Vinyas Maddi

Shraddha Sahay

Gavin Castro Uathavikul

Neha Jain

Heju Jiang

Shawn F Ren

Bing Liu

Embodiments of the disclosed technologies receive first event data associated with a first party application, receive second event data representing a click, in the first party application, on a link to a third party application, receive third event data from the third party application, convert the third event data to a label, map a compressed format of the labeled third event data to the first event data and the second event data to create multi-party attribution data, group multiple instances of the multi-party attribution data into a batch, add noise to the compressed format of the labeled third event data in the batch, and send the noisy batch to a second computing device. A debiasing algorithm can be applied to the noisy batch. The debiased noisy batch can be used to train at least one machine learning model.

On-device privatization of multi-party attribution data

Systems and methods for utilizing machine learning to generate a trans-diagnostic classifier that is operative to concurrently diagnose a plurality of different mental health disorders using a single trans-diagnostic questionnaire that includes a plurality of questions (e.g., 17 questions). Machine learning techniques are used to process labeled training data to build statistical models that include trans-diagnostic item-level questions as features to create a screen to classify groups of subjects as either healthy or as possibly having a mental health disorder. A subset of questions is selected from the multiple self-administered mental health questionnaires and used to autonomously screen subjects across multiple mental health disorders without physician involvement, optionally remotely and repeatedly, in a short amount of time.

Machine learning-based diagnostic classifier

Technologies for providing event-level data privacy for streaming post analytics data include, in some embodiments, receiving a data stream that includes instances of count data collected over a time interval, computing a true count breakdown that includes a set of sub-counts of non-public user interface interactions on the post, creating a noisy count breakdown by applying at least one differential privacy mechanism to the set of sub-counts, and streaming the noisy count breakdown instead of the true count breakdown to a computing device. At least one of the sub-counts is a count that is associated with a particular value of an attribute that has different possible values. The attribute is associated with the non-public user interface interactions on the post.

Event-level data privacy for streaming post analytics data

A system for evaluating mental health of patients includes a memory and a control system. The memory contains executable code storing instructions for performing a method. The control system is coupled to the memory and includes one or more processors. The control system is configured to execute the machine executable code to cause the control system to perform the method: A selection of answers associated with a patient is received. The selection of answers corresponds to each question in a series of questions from mental health questionnaires. Unprocessed MRI data are received. The unprocessed MRI data correspond to a set of MRI images of a biological structure associated with the patient. The unprocessed MRI data is processed to output a set of MRI features. Using a machine learning model, the selection of answers and the set of MRI features are processed to output a mental health indication of the patient.

System and method for identifying transdiagnostic features shared across mental health disorders

A system includes a display device, a user interface, a memory, and a control system. The memory contains machine readable medium including machine executable code storing instructions for performing a method. The control system is coupled to the memory, and includes one or more processors. The control system is configured to execute the machine executable code to cause the control system to display, on the display device, a series of questions from mental health questionnaires. The series of questions includes text and answers for each question. From the user interface, a selection of answers of each of the displayed series of questions is received from a patient. Using a Bayesian Decision List, the received selection of answers is processed to output an indication of mental health of the patient. The indication of mental health identifies a kappa opioid receptor antagonist to which the patient would likely be a higher responder.

Systems and methods for screening, diagnosing, and stratifying patients

Systems and methods for utilizing machine learning to generate a trans-diagnostic classifier that is operative to concurrently diagnose a plurality of different mental health disorders using a single trans-diagnostic questionnaire that includes a plurality of questions (e.g., 17 questions). Machine learning techniques are used to process labeled training data to build statistical models that include trans-diagnostic item-level questions as features to create a screen to classify groups of subjects as either healthy or as possibly having a mental health disorder. A subset of questions are selected from the multiple self-administered mental health questionnaires and used to autonomously screen subjects across multiple mental health disorders without physician involvement, optionally remotely and repeatedly, in a short amount of time.

Techniques for detecting label shift and adjusting training data of predictive models in response are provided. In an embodiment, a first machine-learned model is used to generate a predicted label for each of multiple scoring instances. The first machine-learned model is trained using one or more machine learning techniques based on a plurality of training instances, each of which includes an observed label. In response to detecting a shift in observed labels, for each segment of one or more segments in multiple segments, a portion of training data that corresponds to the segment is identified. For each training instance in a subset of the portion of training data, the training instance is adjusted. The adjusted training instance is added to a final set of training data. The machine learning technique(s) are used to train a second machine-learned model based on the final set of training data.

Label shift detection and adjustment in predictive modeling

The method for evaluating mental health of a patient includes displaying a series of inquiries from mental health questionnaires on a display device. Each inquiry of the series of inquiries includes text and a set of answers. A series of selections is received from a user interface. Each selection of the series of selections is representative of an answer of the set of answers for each corresponding inquiry in the series of inquiries. Unprocessed MRI data are received. The unprocessed MRI data correspond to a set of MRI images of a biological structure associated with a patient. Using a machine learning model, the series of selections and the unprocessed MRI data are processed. The series of selections being processed corresponds to the series of inquiries. A symptom severity indicator for a mental health category of the patient is outputted.

Multimodal biomarkers predictive of transdiagnostic symptom severity

A delayed grouping (batch) processing of previous campaign delivery pacing decisions and corresponding outcomes (deliveries) is used to configure a new auction experiment iteration. In the new iteration, a campaign that was previously over-delivered is classified as either (a) over-delivered due to incorrect pacing or (b) over-delivered due to auction experiment design. After the delayed processing, the new auction experiment iteration is conducted with a mitigating action taken on the previously over-delivered campaign if the campaign is classified as (b) over-delivered due to auction experiment design. For example, the mitigating action can include removing the campaign from a subsequent iteration of the experiment, or the experiment can be redesigned. By doing so, the over-delivery caused by the campaign due to the auction experiment design is avoided when performing the new auction experiment iteration.

Delayed processing for over-delivery determination for content delivery system experimentation

Computer log entries are processed to determine a plurality of baseline rank values associated with a ranking dimension. An overall baseline rank indicator is computed using the determined baseline rank values. For each log data component value combination included in a group of log data component value combinations, a comparison rank value associated with the ranking dimension is determined. Each of the comparison rank values is compared with the overall baseline rank indicator. Based at least in part on the comparisons, one or more log data component value combinations included in the group of log data component value combinations are identified as more anomalous than other log data component value combinations included in the group of log data component value combinations.

Recommending and prioritizing computer log anomalies

A request for an image is received. A reduced version of the image is generated. A plurality of reduced distorted images is generated, wherein each reduced distorted image is a reduced version of a different distortion applied to the image. A variation of quality signature of the image is determined, wherein the variation of quality signature of the image comprises a plurality of element signatures, and wherein the plurality of element signatures are determined based on the plurality of reduced distorted images. The image is categorized into one of a plurality of clusters of images, wherein the categorization is based on a similarity between the variation of quality signature of the image and one or more other variation of quality signatures of one or more other images within the plurality of clusters of images. A distorted version of the image based on the categorization is delivered.

Fast, real-time, estimation of content-sensitive encoding quality for optimized web delivery of images

Growing community of inventors

San Jose, CA, United States of America

Parvez Ahammad