Abstract: Systems and methods described herein relate to determining whether to provide auto-completed values for fields in a digital form. More specifically, for a given field in the digital form, a machine-learning model can be trained to transform an input data set into a predicted field value and can further generate a corresponding confidence metric. A relative-loss parameter can be determined for the field, where the relative-loss parameter represents a loss of responding to an inaccurate predicted field value for the field relative to a loss corresponding to a human user providing a field value for the field. A confidence-metric threshold can be determined for the field based on the relative-loss parameter. For a given usage of the digital form, it can then be determined whether to auto-complete the field with a predicted field value generated by the model by determining whether the corresponding confidence metric exceeds the confidence-metric threshold.

Abstract: The present disclosure relates to systems and methods for a self-adjusting corporation-wide discovery and integration feature of a machine learning system that can review a client's data store, review the labels for the various data schema, and effectively map the client's data schema to classifications used by the machine learning model. The various techniques can automatically select the features that are predictive for each individual use case (i.e., one client), effectively making a machine learning solution client-agnostic for the application developer. A weighted list of common representations of each feature for a particular machine learning solution can be generated and stored. When new data is added to the data store, a matching service can automatically detect which features should be fed into the machine-learning solution based at least in part on the weighted list. The weighted list can be updated as new data is made available to the model.

Abstract: An infrared photodetector including a stack of layers on a substrate having an active area made of organic semiconductor materials capable of converting an infrared radiation into an electric signal and including, in said stack and/or on the substrate, a single layer at least partially filtering visible light.

Abstract: The present disclosure relates to a portable device for collecting and/or concentrating in situ plankton microbiome, configured for submersion in water. The device herein disclosed is a compact and low-cost autonomous biosampler, with the ability to yield DNA samples for later genomic analysis.

Abstract: A server system may match a segment of code for a code integration request to metadata about similar segments of code, wherein the metadata qualifies one or more outcomes of previous integration requests. The server may determine usage rights and rules based on the metadata, wherein some of the usage rights and rules have previously have been approved by a multi-approval workflow that enforces a predetermined process to authorize use of the segment of code for code segment integrations. The server may analyze the metadata to predict an integration score based at least in part on the usage rights and rules of the segments of code. If the integration score of the segment of code exceeds a threshold, the system may automatically generate a data structure for deploying the segment of code, wherein the automatically generating the data structure is performed without the multi-approval workflow.

Abstract: The present invention relates to a metered dose inhaler (MDI) device comprising a mechanically activated visual cue representing a number of doses expelled from, or doses remaining in, a drug-containing cartridge or canister locatable within a body of said MDI, wherein the visual cue is visible through at least a portion of the body of said MDI, and a removable data processing system configured to verify the dose of drug administered and/or inhaled, wherein the MDI device further comprises a correlation system configured to correlate physically released doses from the drug containing cartridge or canister with the administration and/or inhalation data stored in the removable data processing system.

Abstract: The present disclosure relates to systems and methods for using existing data ontologies for generating machine learning solutions for a high-precision search of relevant services to compose pipelines with minimal human intervention. Data ontologies can be used to create a combination of non-logic based and logic-based sematic services that can significantly outperform both kinds of selection in terms of precision. Quality of Service (QoS) and product Key Performance Indicator (KPI) constraints can be used as part of architecture selection in developing, training, validating, and improving machine learning models. For data sets without existing ontologies, one or more ontologies be generated and stored for future use.

Abstract: A server system may match a segment of code for a code integration request to metadata about similar segments of code, wherein the metadata qualifies one or more outcomes of previous integration requests. The server may determine usage rights and rules based on the metadata, wherein some of the usage rights and rules have previously have been approved by a multi-approval workflow that enforces a predetermined process to authorize use of the segment of code for code segment integrations. The server may analyze the metadata to predict an integration score based at least in part on the usage rights and rules of the segments of code. If the integration score of the segment of code exceeds a threshold, the system may automatically generate a data structure for deploying the segment of code, wherein the automatically generating the data structure is performed without the multi-approval workflow.

Abstract: The present disclosure relates to systems and methods for a machine learning platform that generates a library of components to generate machine learning models and machine learning applications. The machine learning infrastructure system allows a user (i.e., a data scientist) to generate machine learning applications without having detailed knowledge of the cloud-based network infrastructure or knowledge of how to generate code for building the model. The machine learning platform can analyze the identified data and the user provided desired prediction and performance characteristics to select one or more library components and associated API to generate a machine learning application. The machine learning can monitor and evaluate the outputs of the machine learning model to allow for feedbacks and adjustments to the model. The machine learning application can be trained, tested, and compiled for export as stand-alone executable code.

Abstract: The present disclosure relates to systems and methods for an intelligent assistant (e.g., a chatbot) that can be used to enable a user to generate a machine learning system. Techniques can be used to automatically generate a machine learning system to assist a user. In some cases, the user may not be a software developer and may have little or no experience in either machine learning techniques or software programming. In some embodiments, a user can interact with an intelligent assistant. The interaction can be aural, textual, or through a graphical user interface. The chatbot can translate natural language inputs into a structural representation of a machine learning solution using an ontology. In this way, a user can work with artificial intelligence without being a data scientist to develop, train, refine, and compile machine learning models as stand-alone executable code.

Abstract: The present disclosure relates to systems and methods for a machine-learning platform for the safe serialization of a machine-learning application. Individual library components (e.g., a pipeline, a microservice routine, a software module, and an infrastructure model) can be encrypted using one or more keys. The keys can be stored in a location different from the storage location of the machine-learning application. Prior to incorporation of the library component into a machine-learning model, one or more keys can be retrieved from the remote storage location to authenticate that the one or more encrypted library components are authentic. The process can reject any of the one or more component, when the encrypted library component fails authentication. If a component is rejected, the system can roll back to a previous, authenticated version of the library component. The authenticated library components can be compiled into machine-learning software.

Abstract: The present disclosure relates to systems and methods for an adaptive pipelining composition service that can identify and incorporate one or more new models into the machine learning application. The machine learning application with the new model can be tested off-line with the results being compared with ground truth data. If the machine learning application with the new model outperforms the previously used model, the machine learning application can be upgraded and auto-promoted to production. One or more parameters may also be discovered. The new parameters may be incorporated into the existing model in an off-line mode. The machine learning application with the new parameters can be tested off-line and the results can be compared with previous results with existing parameters. If the new parameters outperform the existing parameters as compared with ground-truth data, the machine learning application can be auto-promoted to production.

Abstract: The invention relates to an automatic injector device comprising a single-use, disposable, drug delivery assembly comprising a housing and a syringe assembly located at least partially within the housing, said syringe assembly including a plunger, a pre-filled unit-dose drug containing chamber, and needle, said plunger, drug containing chamber and needle being configured and dimensioned to function as an injection syringe; a reusable motorized transmission assembly comprising a housing, a motor and transmission assembly located within the housing, said transmission assembly being configured and dimensioned to engage the plunger of said syringe in the drug delivery assembly and expel said unit dose dmg from the drug containing chamber, into the needle and out of the drug delivery assembly; said single-use disposable drug delivery assembly and said reusable motorized transmission assembly are in substantial axial alignment along a longitudinal axis defined by the syringe, plunger, pre-filled unit-dose drug cont

Abstract: The present disclosure relates to systems and methods for a self-adjusting corporation-wide discovery and integration feature of a machine learning system that can review a client's data store, review the labels for the various data schema, and effectively map the client's data schema to classifications used by the machine learning model. The various techniques can automatically select the features that are predictive for each individual use case (i.e., one client), effectively making a machine learning solution client-agnostic for the application developer. A weighted list of common representations of each feature for a particular machine learning solution can be generated and stored. When new data is added to the data store, a matching service can automatically detect which features should be fed into the machine-learning solution based at least in part on the weighted list. The weighted list can be updated as new data is made available to the model.

Abstract: A server system can receive an input identifying a problem to generate a solution using a machine-learning application. The method selects a machine-learning model template from a plurality of templates based at least in part on the input. The method analyzes one or more formats of the customer data to generate a customer data schema based at least in part a data ontology that applies to the identified problem. The method determines whether the customer data schema is misaligned with one or more key features of the selected machine-learning model template. Based on this determination, the method analyzes the metadata for the selected machine-learning model template to determine what additional information is required to re-align the customer data with the data expectations. The method can include gathering the addition information required to re-align the customer data with the data expectations of the selected machine-learning model template.

Abstract: A server system may receive two or more Quality of Service (QoS) dimensions for the multi-objective optimization model, wherein the two or more QoS dimensions include at least a first QoS dimension and a second QoS dimension. The server system may maximize the multi-objective optimization model along the first QoS dimension, wherein the maximizing includes selecting one or more pipelines for the multi-objective optimization model in the software architecture that meet QoS expectations specified for the first QoS dimension and the second QoS dimension, wherein an ordering of the pipelines is dependent on which QoS dimensions were optimized and de-optimized and to what extent, wherein the multi-objective optimization model is partially de-optimized along the second QoS dimension in order to comply with the QoS expectations for the first QoS dimension, and whereby there is a tradeoff between the first QoS dimension and the second QoS dimension.

Abstract: Dose control device for a handheld pen-type injectable-drug delivery device, the handheld pen-type injectable-drug delivery device comprising an elongate body with a proximal and distal extremity, a longitudinal axis extending from the proximal extremity to the distal extremity, and a rotatable dose setting wheel located at said proximal extremity, wherein said dose control device comprises a magnetic field producing means located at the proximal extremity of said elongate body; one or more magnetic field sensors in communication with a data processing unit located on an outer surface of, or inside, the elongate body; and a clutch assembly configured to selectively move the magnetic field producing means from a first, engaged, position, to a second, disengaged, position.

Abstract: The present invention relates to an add-on device for a metered dose inhaler, an observance improvement system, and a method for improving observance of use in metered dose inhalers, the add-on device comprising an observance system housing component comprising an observance system with at least one pressure sensor; a mouthpiece component configured to fit, surround and removably engage with an exterior surface of a mouthpiece outlet provided on the metered dose inhaler; wherein said observance system housing is configured to fit and removably engage with said mouthpiece component; and said mouthpiece component is specifically adapted to conform to the exterior surface of the mouthpiece outlet of the metered dose inhaler without obstructing delivery of a dose of drug through said outlet.

Abstract: Electronic reading devices provide readers with text on a display, and enhancements to their functionality and efficiency are discussed herein. Text is provided to the reader in an enhanced contrast mode that highlights the active word and line of the text as well as words of interest in the text so as to improve the functionality of the electronic reading device itself as a provider of textual content.

Abstract: Systems, methods, and computer-readable storage media are provided for deleting textual input based upon the input-mode in which such textual input is received. Textual input is received via a block-unit-based input and the textual input is converted into a typewritten text segment and displayed in association with a user computing device. The typewritten text segment includes character-units that substantially comprise at least one recognizable block-unit. Upon receipt of a plurality of delete commands, at least a portion of the typewritten text segment is deleted in accordance with the recognizable block-units. That is, one block-unit is deleted for each delete command received. Upon recognition of a boundary between text received via a block-unit-based input modality and a character-based input modality, the action of the delete command is altered such that one character-unit is deleted for each delete command received in accordance with the input modality.