Abstract: A computer-implemented method includes generating several crypto tokens, each token includes a content portion that is encrypted. For each pair of tokens, a first token and a second token, in response to a correlation score between content portions of the first token and the second token exceeding a predetermined correlation threshold, creating a grid link between the first token and the second token. The tokens are added into a ledger. A group of tokens is created, based on a similarity score. A series of forecasting equations is distributed to the group of tokens. A forecast reveal rate is generated based on the series of forecasting equations, and in response to the forecast reveal rate meeting a forecast threshold, a key is generated for revealing at least one content portions embedded in the group of tokens. The key is released to decrypt the at least one content portion.

Abstract: From a set of natural language text documents, a concept tree is constructed. For a node in the concept tree a polarity of the subset represented by the node is scored. A second set of natural language text documents is added to the subset, the adding resulting in a modified subset of natural language text documents having a polarity score within a predefined neutral polarity score range. From the modified subset, a bin of sentences is selected according to a sentence selection parameter, a sentence in the bin of sentences being extracted from a selected document in the modified subset. A sentence having a factuality score below a threshold factuality score is removed from the bin of sentences. From the filtered bin of sentences a new natural language text document corresponding to the filtered bin of sentences is generated using a transformer deep learning narration generation model.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: Simulating uncertainty in an artificial neural network is provided. Aleatoric uncertainty is simulated to measure what the artificial neural network does not understand from sensor data received from an object operating in a real-world environment by adding random values to edge weights between nodes in the artificial neural network during backpropagation of output data of the artificial neural network and measuring impact on the output data by the added random values to the edge weights between the nodes. Epistemic uncertainty is simulated to measure what the artificial neural network does not know by dropping out a selected node from each respective layer of the artificial neural network during forward propagation of the sensor data and measuring impact of dropped out nodes on the output data of the artificial neural network. An action corresponding to the object is performed based on the impact of simulating the aleatoric and epistemic uncertainty.

Abstract: Synchronizing a sensor network and an ontology by analyzing outputs of a set of sensors, analyzing relationships of an ontology, mapping the outputs to the relationships, identifying a correlation among the outputs, and modifying the ontology according to the correlation.

Abstract: From a set of natural language text documents, a concept tree is constructed. For a node in the concept tree a polarity of the subset represented by the node is scored. A second set of natural language text documents is added to the subset, the adding resulting in a modified subset of natural language text documents having a polarity score within a predefined neutral polarity score range. From the modified subset, a bin of sentences is selected according to a sentence selection parameter, a sentence in the bin of sentences being extracted from a selected document in the modified subset. A sentence having a factuality score below a threshold factuality score is removed from the bin of sentences. From the filtered bin of sentences a new natural language text document corresponding to the filtered bin of sentences is generated using a transformer deep learning narration generation model.

Abstract: From a set of natural language text documents, a concept tree is constructed. For a node in the concept tree a polarity of the subset represented by the node is scored. A second set of natural language text documents is added to the subset, the adding resulting in a modified subset of natural language text documents having a polarity score within a predefined neutral polarity score range. From the modified subset, a bin of sentences is selected according to a sentence selection parameter, a sentence in the bin of sentences being extracted from a selected document in the modified subset. A sentence having a factuality score below a threshold factuality score is removed from the bin of sentences. From the filtered bin of sentences a new natural language text document corresponding to the filtered bin of sentences is generated using a transformer deep learning narration generation model.

Abstract: A relevant factoid(s) related to multimedia data is generated by splitting a multimedia item into a media component and a text component. Text information is retrieved relevant to text data from the text component using a query. The text information is summarized into a factoid. Source data is checked for an image based on the multimedia component. A current state image is generated from the image. The factoid and the current state image are combined into a combined factoid, and the combined factoid is stored for sending to a media outlet for presentation on a media format.

Abstract: A live event virtual experience is provided. Emotions of virtual spectators to a current situation occurring in a live event at a physical venue are determined from received data regarding reactions of the virtual spectators to the live event using bias detection. A historical sound clip that matches the emotions of the virtual spectators to the current situation occurring in the live event is retrieved. The historical sound clip that matches the emotions of the virtual spectators to the current situation occurring in the live event is input into a machine learning model that performs inverse bias mitigation to amplify bias and applies in-process adversarial fairness debiasing. The historical sound clip after performing the inverse bias mitigation to amplify the bias and applying the in-process adversarial fairness debiasing is converted to a standardized historical sound segment length. A sound representation is generated from the standardized historical sound segment length.

Abstract: Provided is a method, a system, and a program product for determining a policy using semi-supervised reinforcement learning. The method includes observing a state of an environment by a learning agent. The method also includes taking an action by the learning agent. The method further includes observing a new state of the environment and calculating a reward for the action taken by the learning agent. The method also includes determining whether a policy related to the learning agent should be changed. The determination is conducted by a teaching agent that inputs the state of the environment and the reward as features. The method can also include changing the policy related to the learning agent upon a determination that a label outputted by the teaching agent exceeds a reward threshold.

Abstract: According to a first aspect of the present invention, there is provided a computer implemented method, a computer system and a computer program product, including training a set of exploitation models, training a set of exploration models, generating a combined exploitation and exploration heat map, and inputting the combined exploitation and exploration heat map into a convoluted neural network.

Abstract: A processor may monitor frequency data related to a user metric of a user during a measurement window. The user metric may relate to the user's use of a computer implemented environment. The processor may simplify the frequency data related to the user metric, resulting in a set of simplified frequency data. The processor may input the set of simplified frequency data into a neural network. The neural network may determine a likelihood of a negative user experience for the user. The processor may alter a parameter of the first user environment based on the likelihood.

Abstract: Edge function-guided artificial intelligence (AI) request routing is provided by applying a machine learning model to predictors of cloud endpoint hydration to determine hydration levels of cloud endpoints, of a hybrid cloud environment, that provide AI processing, determining, for each edge component of a plurality of edge components of the hybrid cloud environment and each cloud endpoint of the cloud endpoints, alternative flow paths between the edge component and the cloud endpoint, the alternative flow paths being differing routes for routing data between the edge component and the cloud endpoint, and the alternative flow paths being of varying flow rates determined based on the hydration levels of the cloud endpoints, and dynamically deploying edge functions on edge component(s), the edge functions configuring the edge component(s) to alternate among the alternative flow paths available in routing AI processing requests from the edge component(s) to target cloud endpoints of the cloud endpoints.

Abstract: The disclosure includes using dilation of speech content from a separated audio input for speech recognition. An audio input from a speaker and predicted changes for the audio input based on an external noise are received at a CNN (Convolutional Neural Network). In the CNN, diarization is applied to the audio input to predict how a dilation of speech content from the speaker changes the audio input to generate a CNN output. A resulting dilation is determined from the CNN output. A word error rate is determined for the dilated CNN output to determine an accuracy for speech to text outputs. An adjustment parameter is set to change a range of the dilation based on the word error rate, and the resulting dilation of the CNN output is adjusted based on the adjustment parameter to reduce the word error rate.

Abstract: Techniques for padding audiovisual clips (for example, audiovisual clips of sporting events) for the purpose of causing the clip to have a predetermined duration so that the padded clip can be evaluated for viewer interest by a machine learning (ML) algorithm. The unpadded clip is padded with audiovisual segment(s) that will cause the padded clip to have a level of viewer interest that it would have if the unpadded clip had been longer. In some embodiments the padded segments are synthetic images generated by a generative adversarial network such that the synthetic images would have the same level of viewer interest (as adjudged by an ML algorithm) as if the unpadded clip had been shot to be longer.

Abstract: The disclosure includes using dilation of speech content from an interlaced audio input for speech recognition. A learning model is initiated to determine dilation parameters for each of a plurality of audible sounds of speech content from a plurality of speakers received at a computer as an audio input. As part of the learning model, a change of each of a plurality of independent sounds is determined in response to an audio stimulus, the independent sounds being derived from the audio input. The disclosure applies the dilation parameters, respectively, based on the change of each of the independent sounds. A voice print is constructed for each of the speakers based on the independent sounds and the dilation parameters, respectively. Speech content is attributed to each of the plurality of speakers based at least in part on the voice print, respectively, and the independent sounds.

Abstract: Distributing computation workload among computing nodes of differing computing paradigms is provided. Compute gravity of each computing node in a cloud computing paradigm and each computing node in a client network computing paradigm within an Internet of Systems is calculated. Each component part of an algorithm is distributed to an appropriate computing node of the cloud computing paradigm and client network computing paradigm based on calculated compute gravity of each respective computing node within the Internet of Systems. Computation workload of each component part of the algorithm is distributed to a respective computing node of the cloud computing paradigm and the client network computing paradigm having a corresponding component part of the algorithm for processing.

Abstract: A live event virtual experience is provided. Emotions of virtual spectators to a current situation occurring in a live event at a physical venue are determined from received data regarding reactions of the virtual spectators to the live event using bias detection. A historical sound clip that matches the emotions of the virtual spectators to the current situation occurring in the live event is retrieved. The historical sound clip that matches the emotions of the virtual spectators to the current situation occurring in the live event is input into a machine learning model that performs inverse bias mitigation to amplify bias and applies in-process adversarial fairness debiasing. The historical sound clip after performing the inverse bias mitigation to amplify the bias and applying the in-process adversarial fairness debiasing is converted to a standardized historical sound segment length. A sound representation is generated from the standardized historical sound segment length.

Abstract: From a set of natural language text documents, a concept tree is constructed. For a node in the concept tree a polarity of the subset represented by the node is scored. A second set of natural language text documents is added to the subset, the adding resulting in a modified subset of natural language text documents having a polarity score within a predefined neutral polarity score range. From the modified subset, a bin of sentences is selected according to a sentence selection parameter, a sentence in the bin of sentences being extracted from a selected document in the modified subset. A sentence having a factuality score below a threshold factuality score is removed from the bin of sentences. From the filtered bin of sentences a new natural language text document corresponding to the filtered bin of sentences is generated using a transformer deep learning narration generation model.

Abstract: Fair deep reinforcement learning is provided. A microstate of an environment and reaction of items in a plurality of microstates within the environment are observed after an agent performs an action in the environment. Semi-supervised training is utilized to determine bias weights corresponding to the action for the microstate of the environment and the reaction of the items in the plurality of microstates within the environment. The bias weights from the semi-supervised training are merged with non-bias weights using an artificial neural network. Over time, it is determined where bias is occurring in the semi-supervised training based on merging the bias weights with the non-bias weights in the artificial neural network. A deep reinforcement learning model that decreases reliance on the bias weights is generated based on determined bias to increase fairness.