Abstract: A method of image compression includes receiving an image. Multiple quantized latent representations are generated to represent features of the image. Each of the quantized latent representations has a different resolution and is generated at staggered timings. Each of the later generated quantized latent representations is conditioned on each of the prior generated quantized latent representations. The multiple quantized latent representations are decoded to reconstruct the image.

Abstract: Methods and systems disclosed herein collect user data in real-time and organize them (e.g., using collaborative filtering) into groups (e.g., clusters). The system then determines statistical distributions of observed real-time intents (e.g., based on actual selections made by users) for each group. The system then merges this distribution with existing model predictions (e.g., a model trained on historical training data) to balance between historical and dynamically updated information.

Abstract: Various techniques are disclosed for computerized tools to discover, form, and analyze dataset interrelations among a system of networked collaborative datasets including a repository configured to receive and store a dataset, and a dataset consolidation system configured to receive data to form a first input to initiate creation of a dataset based on a set of data, to activate a programmatic interface, to transform the set of data from a first format to an atomized format to form an atomized dataset, to monitor the creation of the dataset, to present data representing a status of a portion of the creation of the dataset, to calculate automatically dataset attributes of the linked dataset, to generate a plurality of sub-queries, and to retrieve data representing query results from the at least one of the different data repositories.

Abstract: Techniques are described herein that are capable of creating a language-agnostic computer program repair engine generator. A context-free grammar is annotated to identify token(s) that are likely to be included in or excluded from a computer program in a manner that violates the context-free grammar. A language-agnostic computer program repair engine generator is created that is configured to generate a parser. The repair engine generator is configured to create a repair engine that: converts the candidate string into repaired strings that neither violate the context-free grammar nor violate a criterion for a valid computer program; calculates differences between the candidate string and the respective repaired strings; and replaces the candidate string with a designated repaired string based at least in part on the difference between the designated repaired string and the candidate string being less than or equal to a difference threshold.

Abstract: Techniques are described herein that are capable of synthesizing a computer program to include idiomatic function(s) and semantically-meaningful variable(s) using programming by example. For instance, an intent of a user to synthesize a computer program to include functionality configured to generate sample output(s) from respective input(s) is determined based at least in part on receipt of the sample input(s) and the respective sample output(s) from the user. Based at least in part on the determined intent, the computer program is synthesized to include the idiomatic function(s) by configuring the idiomatic function(s) to have the target functionality and to conform to a convention of the target domain-specific language associated with a textual representation of the computer program to be displayed to the user. Non-semantically-meaningful variable(s) included among the idiomatic function(s) are replaced with the respective semantically-meaningful variable(s).

Abstract: Various techniques are described for platform management of integrated access of public and privately-accessible datasets utilizing federated query generation and query schema rewriting optimization, including receiving at a dataset access platform a query formatted according to a first data schema, generating a copy of the query, saving the query and the copy to a datastore, parsing the copy of the query in the first schema using an inference engine, determining whether the query comprises data associated with an access control condition associated with accessing the dataset, the access control condition being configured to indicate whether the query is permitted to access the dataset, and rewriting, using a proxy server, the copy of the query in a second schema by converting the copy of the query into a triple associated with the query and another triple associated with the access control condition.

Abstract: Methods and systems are described for generating dynamic interface options using machine learning models. The dynamic interface options may be generated in real time and reflect the likely goals and/or intents of a user. The machine learning model may provide these features by interpreting multi-modal feature inputs. For example, the machine learning model may include a first machine learning model, wherein the first machine learning model comprises a convolutional neural network, and a second machine learning model, wherein the second machine learning model performs a Weight of Evidence (WOE) analysis.

Abstract: Various embodiments relate generally to data science and data analysis, computer software and systems, and wired and wireless network communications to provide an interface between repositories of disparate datasets and computing machine-based entities that seek access to the datasets, and, more specifically, to a computing and data storage platform that facilitates consolidation of one or more datasets, whereby a collaborative data layer and associated logic facilitate, for example, efficient access to, and implementation of, collaborative datasets. In some examples, a method may include receiving data representing a query of a consolidated dataset that may include datasets formatted atomized datasets, analyzing the query to classify portions of the query to form classified query portions, partitioning the query into sub-queries as a function of a classification type for each of the classified query portions, and retrieving data representing a query result from distributed data repositories.

Abstract: Pasting content from a clipboard buffer as structured tabular data. A computer system determines a data type of content within a clipboard buffer. Based on the data type of the content, the computer system identifies a tabular pattern analysis technique to apply to the content. Based on applying the tabular pattern analysis technique to the content, the computer system identifies a portion of tabular content within the content. Using a clipboard application programming interface, the computer system presents the portion of tabular content to an application as paste data that is structured as a set of rows and a set of columns.

Abstract: Distinguishing pattern differences from non-pattern differences. A set of differences is identified. The set comprises a plurality of differences between first and second versions of a document. A pattern is identified. The pattern explains a transformation from a first string in the first version of the document to a second string in the second version of the document. A subset of differences are identified. The subset comprises a plurality of differences, from among the set, which match the pattern. While presenting a user interface that visually highlights differences between the first and second versions of the document, a first visual treatment is applied to a first difference, based on the first difference being included in the subset. A second visual treatment is also applied to a second difference, based on the second difference being excluded from the subset. The second visual treatment is different than the first visual treatment.

Abstract: Methods and systems are described herein for generating dynamic conversational responses. For example, dynamic conversational responses may facilitate an interactive exchange with users. Therefore, the methods and systems used specialized methods to enriched data that may be indicative of a user's intent prior to processing that data through the machine learning model, as well as a specialized architecture for the machine learning models that take advantage of the user interface format. For example, a first machine learning model may be trained using a multi-class cross entropy loss function, and a second machine learning model may be trained using a binary cross entropy loss function. A third output may be determined based on a weighted average of first and second outputs from the first and second machine learning models, and a subset of dynamic conversational responses may be generated based on the determined third output.

Abstract: Methods and systems are described herein for generating dynamic conversational responses. For example, dynamic conversational responses may facilitate an interactive exchange with users. Therefore, the methods and systems used specialized methods to enriched data that may be indicative of a user’s intent prior to processing that data through the machine learning model, as well as a specialized architecture for the machine learning models that take advantage of the user interface format.

Abstract: Methods and systems are described for generating dynamic interface options using machine learning models. The dynamic interface options may be generated in real time and reflect the likely goals and/or intents of a user. The machine learning model may provide these features by interpreting multi-modal feature inputs. For example, the machine learning model may include a first machine learning model, wherein the first machine learning model comprises a convolutional neural network, and a second machine learning model, wherein the second machine learning model performs a Weight of Evidence (WOE) analysis.

Abstract: Various embodiments relate generally to data science and data analysis, computer software and systems, and wired and wireless network communications to provide an interface between repositories of disparate datasets and computing machine-based entities that seek access to the datasets, and, more specifically, to a computing and data storage platform that facilitates consolidation of one or more datasets, whereby a collaborative data layer and associated logic facilitate, for example, efficient access to, and implementation of, collaborative datasets. In some examples, a method may include receiving a dataset having a data format into a dataset ingestion controller configured to form a collaborative dataset, interpreting data of the dataset against data classifications at an inference engine to derive at least an inferred attribute, associating the data with annotative data identifying the inferred attribute, and converting the dataset at a format converter to form an atomized dataset.

Abstract: Embodiments use a multi-modal approach to generate software programs that match a solution program description. The solution program description may include natural language, input-output examples, partial source code, desired operators, or other hints. Some embodiments use optimized prompts to a pre-trained language model to obtain initial candidate programs. Maximal program components are extracted and then recombined variously using component-based synthesis. Beam search reduces a solution program search space by discarding some candidates from a given synthesis iteration. Relevance metrics, string similarity metrics, operator frequency distributions, token rareness scores, and other optimizations may be employed. By virtue of optimizations and the multi-modal approach, a solution program may be obtained after fewer iterations than by use of a language model alone.

Abstract: A processor-implemented method for video compression using an artificial neural network (ANN) includes receiving a video via the ANN. The ANN extracts a first set of features of a current frame of the video and a second set of features of a reference frame of the video. The ANN determines an estimate of correlation features between the first set of features of the current frame and the second set of features of the reference frame. The estimate of the correlation features are encoded and transmitted to a receiver.

Abstract: A method for monitoring a working environment of a movable device utilizing a monitoring apparatus, wherein the working environment includes a working area and at least one protected area and the movable device is located within the working area during normal operation of said movable device, where the method includes a user inputting a plurality of convex polytopes into the monitoring apparatus, the convex polytopes corresponding to areas in which the movable device is located during normal operation, determining a convex polytope hull using the monitoring apparatus, the convex polytope hull completely enclosing the multiplicity of convex polytopes, and determining the at least one protected area by calculating a difference from the convex polytope hull and the input using the monitoring apparatus, such that monitoring of the position of the movable device is simplified because the working area can be modeled autonomously.

Abstract: An Integrated Circuit with an automatically re-tuning analog circuit is provided. The Integrated Circuit comprises (a) an analog circuit comprising a plurality of tunable components each configured to respond to a plurality of change control bits, (b) a Process, Voltage Temperature (PVT) characteristics monitor comprising a plurality of PVT sensors, (c) a tuning memory embedded with a machine learning (ML) model of the analog circuit and (d) an artificial intelligence (AI) engine configured to receive a PVT signal input from the plurality of PVT sensors and the machine learning model embedded in the tuning memory. Each tunable component is configured to change its electrical characteristics such that together each of the tunable components is enabled to retune the analog circuit to attain a predefined set of electrical characteristics.

Abstract: The present invention relates to a body monitoring system comprising a patch, the patch comprising a main body, the main body comprising a second face suitable for facing the skin of a user, the patch comprising an adhesive layer at least partially covering the second face, and a peelable cover covering the adhesive layer, the peelable cover comprising at least two separate portions, the portions being adjacent to each other, the main body and the adhesive layer comprise a central portion forming an opening suitable for receiving the capsule, the opening having a maximum diameter greater than 2 mm, preferably greater than 5 mm.

Abstract: A processor-implemented method for image compression using an artificial neural network (ANN) includes receiving, at an encoder of the ANN, an image and a spatial segmentation map corresponding to the image. The spatial segmentation map indicates one or more regions of interest. The encoder compresses the image according to a controllable spatial bit allocation. The controllable spatial bit allocation is based on a learned quantization bin size.