Abstract: Systems, methods, and computer-readable medium are provided for healthcare analysis. Data corresponding to a plurality of patients is received. The data is parsed to generate normalized data for a plurality of variables, with normalized data generated for more than one variable for each patient. A causal relationship network model is generated relating the plurality of variables based on the generated normalized data using a Bayesian network algorithm. The causal relationship network model includes variables related to a plurality of medical conditions or medical drugs. In another aspect, a selection of a medical condition or drug is received. A sub-network is determined from a causal relationship network model. The sub-network includes one or more variables associated with the selected medical condition or drug. One or more predictors for the selected medical condition or drug are identified.

Abstract: A method performed by a local client computing device is provided. The method includes training a local model using data from the local client computing device, resulting in a local model update; sending the local model update to a central server computing device; receiving from the central server computing device a first updated global model; determining that the first updated global model does not meet a local criteria, wherein determining that the first updated global model does not meet a local criteria comprises computing a score based on the first updated global model, wherein the score exceeds a threshold; in response to determining that the first updated global model does not meet a local criteria, sending to the central server computing device context information; and receiving from the central server computing device a second updated global model.

Abstract: A learning apparatus according to the present application includes: a dividing unit that divides predetermined learning data features of which are to be learned by a model by training, into a plurality of sets in chronological order; and a training unit that trains the model to learn the features of the learning data included in the set obtained by the division by the dividing unit, for each of the divided sets, in a predetermined order.

Abstract: A method includes training a first control model by utilizing a first set of input data as first input, resulting in a trained first control model; copying the trained first control model to a second control model, wherein, after copying, the second input layer and the plurality of second hidden layers is identical to the plurality of first hidden layers, and the first output layer is replaced by the second output layer; freezing the plurality of second hidden layers; training the second control model by utilizing the first set of input data as second input, resulting in a trained second control model; and running the trained second control model by utilizing a second set of input data as second input, wherein the second output outputs the quality measure of the first control model.

Abstract: A parameter optimization device 800 optimizes input CNN structure information and outputs optimized CNN structure information, and includes stride and dilation use layer detection means 811 for extracting stride and dilation parameter information for each convolution layer from the input CNN structure information, and stride and dilation use position modification means 812 for changing the stride and dilation parameter information of the convolution layer.

Abstract: A multi-task deep learning network and a generation method thereof are provided. The generation method of a multi-task deep learning network includes: building at least one shared layer, where the shared layer is configured to receive a plurality of pieces of input information and generate a plurality of pieces of processed feature information; building a plurality of groups of task-specific layers, wherein the groups of task-specific layers compute and generate a plurality of groups of output information corresponding to a plurality of different tasks according to the pieces of processed feature information; and activating at least one of the groups of task-specific layers in stages according to a power supply state of an electronic apparatus.

Abstract: Techniques are provided for evaluation of machine learning models using agreement scores. One method comprises obtaining two or more of: (i) a first set of quantitative features characterizing model parameters of a machine learning model; (ii) a second set of quantitative features characterizing a training process used to train the machine learning model; and (iii) a third set of quantitative features characterizing a training dataset used to train the machine learning model; generating a score based on an aggregation of at least portions of the two or more of the first set, the second set and the third set, wherein the score is based on an agreement of the machine learning with designated characteristics; and initiating an automated action based on the score. The automated action may comprise updating the machine learning model; generating a notification in connection with an audit; and/or selecting a machine learning model for deployment.

Abstract: A method and system for odor visual expression based on electronic nose technology, and a storage medium are disclosed. The method includes: acquiring category information of an odor to be identified based on the electronic nose technology; determining demand information of the odor to be identified according to the category information; collecting corresponding relevant data according to the demand information so as to construct a database; constructing a knowledge map centered on odor identification according to the database; and converting the structured knowledge map into a visual node-link graph. The method and system for odor visual expression based on electronic nose technology and the storage medium according to this disclosure present related information of the identified odor to users in a form of visual content, and the visual content can facilitate the users to have more intuitive understanding of odors.

Abstract: A computing system includes a machine learning algorithm executing a machine learning model to predict a probability of a fracture driven interaction associated with a hydrocarbon well. The machine learning algorithm trains the machine learning model using well treatment pumping data, offset well production data, and well stage data. Feature extraction is performed on the pumping data, production data, and well stage data to produce a machine learning model that is used to predict the probability of a fracture driven interaction. The resulting machine learning model can be deployed for use in ongoing hydraulic fracturing operations to predict and reduce real-time fracture driven interactions.

Abstract: At least one processor can receive at least one preliminary response generated by a machine learning (ML) model having a predetermined level of randomness. The at least one processor can determine at least one transformation applying a new level of randomness, different from the predetermined level of randomness, to the at least one preliminary response. The at least one processor can generate at least one modified preliminary response, the generating comprising applying the at least one transformation to the at least one preliminary response. The at least one processor can replace the at least one preliminary response with the at least one modified preliminary response within the ML model, wherein the ML model generates a final response using the at least one modified preliminary response.

Abstract: Systems and methods for generating a knowledge base for facilitating interactions between users and an automated assistant. An example method is performed by one or more processors of a computing system. The example method may include receiving a transmission over a communications network from a computing device, the transmission including a plurality of transcripts of user interactions with the automated assistant or agents associated with the computing system, transforming ones of the transcripts into one or more question-and-answer (Q & A) pairs associated with a subject of the corresponding user interaction, and embedding ones of the Q & A pairs as vectors in a vector space for retrieval by the automated assistant during subsequent user interactions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned identification of radio frequency (RF) signals.

Abstract: An iterative attention-based neural network training and processing method and system iteratively applies a focus of attention of a trained neural network on syntactical elements and generates probabilities associated with representations of the syntactical elements, which in turn inform a subsequent focus of attention of the neural network, resulting in updated probabilities. The updated probabilities are then applied to generate syntactical elements for delivery to a user. The user may respond to the delivered syntactical elements, providing additional training information to the trained neural network.

Abstract: An iterative attention-based neural network training and processing method and system iteratively applies a focus of attention of a trained neural network on syntactical elements and generates probabilities associated with representations of the syntactical elements, which in turn inform a subsequent focus of attention of the neural network, resulting in updated probabilities. The updated probabilities are then applied to generate syntactical elements for delivery to a user. The user may respond to the delivered syntactical elements, providing additional training information to the trained neural network.

Abstract: In accordance with some embodiments, systems, methods, and media for generating and using neural networks having improved efficiency for analyzing video are provided. In some embodiments, the method comprises: providing image data to a trained neural network; receiving, at a neuron, a delta-based input ?in from a previous layer; generating an output g(?in) of a linear transform g; generating an updated state variable a based on g(?in) and a current a; generating an output ƒ(a) of an activation function ƒ based on updated a; generating an updated state variable d based on a current d, a state variable b, and ƒ(a); generating an updated b based on output ƒ(a); transmitting d to a next layer based on a transmission policy and subtracting the value from d; and receiving an output from the trained neural network that represents a prediction based on the image data.

Abstract: Provided is a system for generating an inference based on real-time selection of a machine learning model using a machine learning model framework that includes at least one processor programmed or configured to receive a request for inference, wherein the request includes a payload, select a machine learning model of a plurality of machine learning models based on the request for inference, determine an aggregation of data based on the machine learning model and the payload of the request, transform the aggregation of data into inference data, wherein the inference data has a configuration that is capable of being processed by the machine learning model, and generate an inference based on the inference data using the machine learning model. Methods and computer program products are also provided.

Abstract: Memory context for large language model classification override performing operations including obtaining a document and initiating processing the document through a shared large language model to generate an LLM classification in a set of classifications. The operations further include processing the document through an embedding generation model to generate a value embedding for the document, comparing the value embedding with stored value embeddings for a user, and overriding, in the set of classifications, the LLM classification with a stored value classification when a corresponding stored embedding in the stored embeddings matches the value embedding. The operations further include updating a data repository with the set of classifications.

Abstract: A computer-implemented method for compressing a machine learning model includes converting an input machine learning model into a standard machine learning model. The method further includes converting the standard machine learning model into a plurality of pruned machine learning models, each of the pruned machine learning models converted using a corresponding pruning ratio from a pruning ratio candidate list. The method further includes determining, for each of the pruned machine learning models, a size-to-error ratio. The method further includes selecting, based on the size-to-error ratio of the pruned machine learning models, a first pruning ratio from the pruning ratio candidate list. The method further includes generating a compressed machine learning model by compressing the input machine learning model using the first pruning ratio that is selected. The method further includes deploying the compressed machine learning model for production.

Abstract: An approach is disclosed that receives, at a computer system, a set of biometric data readings pertaining to a user of the system. The biometric data readings are received from biometric sensors that are near the user. After receiving the biometric readings, an audible notification is transmitted to the user. Subsequently, a second set of biometric data readings pertaining to the user from the biometric sensors that are proximate to the user. The first and second sets of biometric data readings are compared with the comparison resulting in a confidence level that the user heard the transmitted audible notification. The audible notification is retransmitted in response to the confidence level being below a threshold not retransmitted in response to the confidence level meeting the threshold indicating that the user heard the first transmission.

Abstract: A model deployment tuning system (MDTS) receives a trained ML model, specified constraints, and model evaluation data and applies a plurality of model utilization techniques to the trained ML model to produce a plurality of useable model versions of the trained ML model. The MDTS executes each of the plurality of useable model versions of the trained ML models on a plurality of different compute instance types using the model evaluation data to produce model evaluation results for a plurality of different combinations. The MDTS filters the model evaluation results based on the specified constraints to indicate one or more of the different combinations satisfying the specified constraints. The MDTS deploys one of the plurality of useable model versions of the trained ML model to a compute instance types according to a selected combination satisfying the specified constraints.