Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage medium, for machine unlearning. In one aspect a method includes receiving a request to remove a client dataset from a machine learning model, the model being associated with noise sensitivities determined during training of the model on respective client datasets including the client; and in response to receiving the request: identifying, from stored noise sensitivities of the client, a most recent training iteration that produced a noise sensitivity that is below a predetermined threshold that is based on a noise standard deviation and predefined target privacy parameters; updating parameters of the model, comprising adding noise to model parameters for the most recent training iteration; and performing subsequent iterations of training of the model, wherein the model is initialized with the updated parameters and the subsequent iterations train the model on datasets excluding the dataset owned by the client.

Abstract: Aspects of the present disclosure provide systems, methods, apparatus, and computer-readable storage media that support improved watermarking and fingerprinting of a shared dataset. To illustrate, clustering may be performed on the dataset using initial clustering parameters (e.g., a secret key) to assign each record (e.g., attribute) of the dataset to one of multiple clusters. The secret key may be selected by a user or determined automatically based on the clustering algorithm. After the clustering, the records of each cluster may be selected for embedding a portion of fingerprint data based on one or more security parameters (e.g., a hash function, priority values, even/or selection, etc.). The selected records (or portions thereof) may be replaced with corresponding portions of the fingerprint data to embed the fingerprint data within different records as watermarking. Aspects also include analyzing a dataset to verify whether watermarking is present and to extract a fingerprint.

Abstract: Systems and methods for smart incentivization for achieving collaborative machine learning are disclosed. A system receives local model parameters from plurality of client devices in a network, for global model corresponding to collaborative machine learning. The system determines an optimum score for each client device using pre-trained Conditional Variational Auto Encoder (CVAE), based on local model parameter. The system computes contribution score for each client device by determining relative distance value of optimum score corresponding to each client device with optimum score corresponding to another client device from the plurality of client devices, and a global model optimum score of global model. The system updates global model with local model parameter received from the selected set of client devices of the plurality of client devices corresponding to good class, average class, and bad class.

Abstract: A system for providing visual content optimization is disclosed. The system may comprise a data access interface, a processor, and an output interface. The data access interface may receive data associated with a design or graphical layout from a data source, and receive priority parameters. The processor may identify a plurality of discrete design elements from the design or graphical layout. The processor may create a new design or graphical layout based on the plurality of discrete design elements and on priority parameters. The processor may also evaluate the new design or graphical layout based on an evaluation technique. In some examples, the evaluation technique may include a visual attention prediction subsystem to determine the most visually appealing design using artificial intelligence (AI) or machine learning. The processor may also select the new design or graphical layout based on a selection technique.

Abstract: Examples of a system for usage control of a personal data are described. The system may obtain an input image including a first face of a person. Further, the system may compute a usage control matrix based on the input image, at least one usage control function, and a predefined criteria. The pre-defined criteria may be associated with at least one of: a data usage policy, a face matching probability related to matching of the face present in the input image, and a face recognition probability related to a recognition of an identity of the person. Furthermore, by using the input image and the usage control matrix, the system may transform the input image to a usage-controlled image. Furthermore, the system may verify a matching of the face present in the input image with a second face present in the usage-controlled image.

Abstract: A system comprises a receiver to receive a main content. The system further comprises a detector to detect a placeholder in the main content for placement of a media object. Further, the system comprises an obtainer to obtain a plurality of media objects having placement attributes corresponding to the placeholder in the main content, where a placement attribute is indicative of characteristics of a media object compatible with the placeholder. The system further comprises a selector to select one of the plurality of media objects for being placed in the placeholder of the main content, based on a user profile. Further, the system comprises a generator to generate a final content indicative of the selected media object embedded in the main content.

Abstract: A system and method for facilitating a rule-based anonymization of an original dataset is disclosed. The system may include a processor including a data privacy evaluator and a rules engine. The data privacy evaluator may receive at least one anonymized dataset corresponding to a predefined strategy of anonymization. The at least one anonymized dataset may include a variation from the original dataset by at least one of a privacy metric and a consistency metric. The data privacy evaluator may evaluate the at least one anonymized dataset and may generate a final output value based on a first output and a second output. The processor may assess the final output value with respect to a predefined threshold through the rules engine. If the final output value may be equal or higher than the predefined threshold, the system may permit an access to the anonymized dataset.

Abstract: Systems, apparatuses, and methods are directed toward determining emotional states of a subject. For example, the systems, apparatuses, and methods determine one or more previous characteristics of a pupil of an eye based on image data from eye tracking sensors, determine one or more current characteristics of the pupil based on image data from the eye tracking sensors, where the one or more current characteristics include one or more of a current position of the pupil or a current size of the pupil, track movements, based on image data from the eye tracking sensors, in a position of the pupil and changes in a size of the pupil over a time period, automatically predict an emotional state based on a comparison between the one or more previous characteristics and the one or more current characteristics, the tracked movements and the tracked changes in the size and adjust a parameter of one or more hardware devices based on the predicted emotional state.

Abstract: Examples of a system for usage control of a personal data are described. The system may obtain an input image including a first face of a person. Further, the system may compute a usage control matrix based on the input image, at least one usage control function, and a predefined criteria. The pre-defined criteria may be associated with at least one of: a data usage policy, a face matching probability related to matching of the face present in the input image, and a face recognition probability related to a recognition of an identity of the person. Furthermore, by using the input image and the usage control matrix, the system may transform the input image to a usage-controlled image. Furthermore, the system may verify a matching of the face present in the input image with a second face present in the usage-controlled image.

Abstract: A system for providing visual content optimization is disclosed. The system may comprise a data access interface, a processor, and an output interface. The data access interface may receive data associated with a design or graphical layout from a data source, and receive priority parameters. The processor may identify a plurality of discrete design elements from the design or graphical layout. The processor may create a new design or graphical layout based on the plurality of discrete design elements and on priority parameters. The processor may also evaluate the new design or graphical layout based on an evaluation technique. In some examples, the evaluation technique may include a visual attention prediction subsystem to determine the most visually appealing design using artificial intelligence (AI) or machine learning. The processor may also select the new design or graphical layout based on a selection technique.

Abstract: A system for providing visual content optimization is disclosed. The system may comprise a data access interface, a processor, and an output interface. The data access interface may receive data associated with a design or graphical layout from a data source, and receive priority parameters. The processor may identify a plurality of discrete design elements from the design or graphical layout. The processor may create a new design or graphical layout based on the plurality of discrete design elements and on priority parameters. The processor may also evaluate the new design or graphical layout based on an evaluation technique. In some examples, the evaluation technique may include a visual attention prediction subsystem to determine the most visually appealing design using artificial intelligence (AI) or machine learning. The processor may also select the new design or graphical layout based on a selection technique.

Abstract: Examples of the disclosure enable an information processing system to automatically implement a user interaction diagnostic engine. In some examples, the information processing system analyzes documents to identify parameters associated with profile features and performance metrics. Based on the parameters, correlation values between the profile features and one or more performance metrics are determined. Based on the correlation values, at least one profile feature is identified to improve a parameter associated with the performance metrics. A predictive model associated with the profile features and the performance metrics is generated. One or more actionable items configured to modify the at least one profile feature are determined such that, based on the predictive model, a parameter associated with the performance metrics are predicted to improve upon execution of the one or more actionable items.

Abstract: Systems, apparatuses, and methods are directed toward determining emotional states of a subject. For example, the systems, apparatuses, and methods determine one or more previous characteristics of a pupil of an eye based on image data from eye tracking sensors, determine one or more current characteristics of the pupil based on image data from the eye tracking sensors, where the one or more current characteristics include one or more of a current position of the pupil or a current size of the pupil, track movements, based on image data from the eye tracking sensors, in a position of the pupil and changes in a size of the pupil over a time period, automatically predict an emotional state based on a comparison between the one or more previous characteristics and the one or more current characteristics, the tracked movements and the tracked changes in the size and adjust a parameter of one or more hardware devices based on the predicted emotional state.

Abstract: A system for providing visual content optimization is disclosed. The system may comprise a data access interface, a processor, and an output interface. The data access interface may receive data associated with a design or graphical layout from a data source, and receive priority parameters. The processor may identify a plurality of discrete design elements from the design or graphical layout. The processor may create a new design or graphical layout based on the plurality of discrete design elements and on priority parameters. The processor may also evaluate the new design or graphical layout based on an evaluation technique. In some examples, the evaluation technique may include a visual attention prediction subsystem to determine the most visually appealing design using artificial intelligence (AI) or machine learning. The processor may also select the new design or graphical layout based on a selection technique.

Abstract: A system for placement of media object in a video feed comprises a receiver to receive the video feed, a tracker to receive a camera tracking data regarding movement of a camera capturing the video feed, a detector to detect a placeholder within the video feed where the media object may be placed and detect an attribute, such as size and position of the placeholder, and a media obtainer to obtain information regarding the media object, the media object having a placement attribute corresponding to the placeholder. The system also comprises an aligner to adjust the placement attribute of the media object with the attribute of the placeholder for positioning the media object within the placeholder, and a content generator to generate a content indicative of the media object embedded within the placeholder of the video feed.

Abstract: A system for placement of media object in a video feed comprises a receiver to receive the video feed, a tracker to receive a camera tracking data regarding movement of a camera capturing the video feed, a detector to detect a placeholder within the video feed where the media object may be placed and detect an attribute, such as size and position of the placeholder, and a media obtainer to obtain information regarding the media object, the media object having a placement attribute corresponding to the placeholder. The system also comprises an aligner to adjust the placement attribute of the media object with the attribute of the placeholder for positioning the media object within the placeholder, and a content generator to generate a content indicative of the media object embedded within the placeholder of the video feed.

Abstract: A system comprises a receiver to receive a main content. The system further comprises a detector to detect a placeholder in the main content for placement of a media object. Further, the system comprises an obtainer to obtain a plurality of media objects having placement attributes corresponding to the placeholder in the main content, where a placement attribute is indicative of characteristics of a media object compatible with the placeholder. The system further comprises a selector to select one of the plurality of media objects for being placed in the placeholder of the main content, based on a user profile. Further, the system comprises a generator to generate a final content indicative of the selected media object embedded in the main content.

Abstract: The invention concerns a system having: a virtual assistant interactivity platform (102) including: a processing device; a memory device storing data identifying a plurality of virtual assistants, and one or more topics associated with each virtual assistant; a communication interface configured to receive an input query from a user device (104); and a memory coupled to the processing device and storing executable instructions that, when executed by the processing device, cause the processing device to: assess the input query to identify a subset of at least one of the virtual assistants based on a comparison between at least one topic of the query and the one or more topics associated with each virtual assistant; transmit a query based on the input query to each of the virtual assistants of the subset; evaluate answers to the input query received from the virtual assistants of the subset in order to generate a response comprising one or more of the answers; and transmit the response to the user device.

Abstract: Examples of the disclosure enable an information processing system to automatically generate a common data repository including a plurality of documents. In some examples, the information processing system is configured to analyze the documents to identify a plurality of topics. Based on the identified topics, the documents are classified into a plurality of sets. A set is associated with a corresponding topic. One or more correlations between the documents are identified and, based on the identified correlations, one or more user interaction tools are generated including an interaction script.

Abstract: Intelligent receipt scanning and analysis may include scanning a receipt that includes information related to a product. The information related to the product may be transformed to text, and extracted from the text by utilizing a machine learning process. The extracted information may be compared to known information for a plurality of known products to identify the product as a known product of the plurality of known products or an unknown product. The extracted information related to the product and known product information, from the known information, for the known product of the plurality of known products may be analyzed in response to a determination that the extracted information is similar to the known product information for the known product of the plurality of known products.