Abstract: A method with quantization for a deep learning model includes: determining a second model by quantizing a first model based on a quantization parameter; determining a real value of multi optimization target parameter by testing the second model; calculating a loss function based on the real value of the multi optimization target parameter, an expected value of the multi optimization target parameter, and a constraint value of the multi optimization target parameter; updating the quantization parameter based on the loss function and using the second model as the first model; iteratively executing the foregoing operations until a preset condition is satisfied; and in response to the preset condition being satisfied, determining an optimal quantization parameter and using, as a final quantization model, the first model that executes quantization based on the optimal quantization parameter.

Abstract: Described herein are methods and a system for analyzing the impact of multiple components with one another that support a cloud service. Events are collected in time series from the components and aggregated in a relationship tree that groups the components. Propositions as to the events are created from which a conjunctive normal form (CNF) statement is derived. The CNF statement is converted to one or more directed acyclic graphs (DAG). The DAGs are traversed to determine TRUE values used to provide remediations solutions.

Abstract: A computer-implemented method, system, and computer program product to solve a cognitive task that includes learning abstract properties. One embodiment may comprise accessing datasets that characterize the abstract properties. The accessed datasets may then be inputted into a first neural network to generate first embeddings. Pairs of the first embeddings generated may be formed, which correspond to pairs of the datasets. Data corresponding to the pairs formed may then be inputted into a second neural network, which may be executed to generate second embeddings. The latter may capture relational properties of the pairs of the datasets. A third neural network may be subsequently executed, based on the second embeddings generated, to obtain output values. One or more abstract properties of the datasets are learned based on the output values obtained, in order to solve the cognitive task.

Abstract: Embodiments relate to a neural processor circuit that includes a kernel access circuit and multiple neural engine circuits. The kernel access circuit reads compressed kernel data from memory external to the neural processor circuit. Each neural engine circuit receives compressed kernel data from the kernel access circuit. Each neural engine circuit includes a kernel extract circuit and a kernel multiply-add (MAD) circuit. The kernel extract circuit extracts uncompressed kernel data from the compressed kernel data. The kernel MAD circuit receives the uncompressed kernel data from the kernel extract circuit and performs neural network operations on a portion of input data using the uncompressed kernel data.

Abstract: Systems and methods for building and querying an architecture knowledge graph are disclosed. In one aspect, a method includes determining an intended state and a functional state of a plurality of evaluated architectures of an evaluating organization; generating a knowledge graph, including an intended state dimension and a functional state dimension based on the determined intended state and the functional state, respectively, of the plurality of evaluated architectures; receiving, at a query engine, a natural language query; processing the natural language query with a natural language query processing engine; generating, as a result of processing the natural language query, a plurality of graph properties; querying the architecture knowledge graph using the plurality of graph properties as parameters; and displaying the results of the querying through an interface.

Abstract: A learning content evaluation apparatus includes a problem information processing unit configured to generate a problem embedding vector on the basis of problem information included in pre-collected problem content; an artificial intelligence (AI) model training unit configured to generate AI learning information including a weight determined using a result of training an AI model on the basis of the problem embedding vector and a user embedding vector, in which solution result data of a user for the pre-collected problem content is reflected; and a correct answer probability prediction unit configured to calculate correct answer probability information about a probability of being answered correctly by the user for the added problem, on the basis of a problem embedding vector of the added problem content and the AI learning information.

Abstract: Training an encoder is provided. The method comprises inputting a current state of a number of aircraft into a recurrent layer of a neural network, wherein the current state comprises a reduced state in which a value of a specified parameter is missing. An action applied to the aircraft is input into the recurrent layer concurrently with the current state. The recurrent layer learns a value for the parameter missing from current state, and the output of the recurrent layer is input into a number of fully connected hidden layers. The hidden layers, according to the current state, learned value, and current action, determine a residual output that comprises an incremental difference in the state of the aircraft resulting from the current action.

Abstract: Systems and methods for performing multiple locally stored artificial neural network (ANN) computations are provided. An example method comprises receiving, by one or more processing units, an ANN dataset associated with at least one ANN of a plurality of ANNs; storing, by processing units, the ANN dataset in a memory coupled to the processing units; associating, by the processing units, a base address with the at least one ANN, wherein the base address is to be used to locate the ANN dataset in the memory; keeping, by the processing units, the ANN dataset in the memory; receiving, by the processing units, an input dataset and the base address; determining, by the processing units and based on the base address, a location of the ANN dataset in the memory; and performing, by the processing units, ANN computation using the ANN dataset and input dataset.

Abstract: Described herein are systems and methods for state change implementation. In some embodiments, an apparatus may obtain system data and classify the system data to descriptors. In some embodiments, an apparatus may determine descriptor ratios as a function of the elements of system data classified to descriptors, weightings associated with the elements of system data, or both. In some embodiments, an apparatus may determine a growth model as a function of a plurality of descriptor ratios.

Abstract: An apparatus for enhancing longevity, wherein the apparatus includes at least a processor and a memory communicatively connected to the processor, the memory containing instructions configuring the at least a processor to receive a longevity measurement related to a user and calculate a longevity parameter as a function of the longevity measurement. The memory containing instructions further configuring the processor to assign the user a longevity level, including training a longevity classifier using a longevity training data containing a plurality of data entries correlating examples of longevity parameters to examples of longevity levels, classifying the longevity parameter to the longevity level using the longevity classifier, and assigning the user the longevity level as a function of the classification. The memory containing instructions further configuring the processor to generate a longevity plan as a function of the longevity parameter and longevity level.

Abstract: Systems and methods ingest extensive data regarding parties and contextual data to determine correlation between a variety of data types, parameters related thereto, and member service representative (MSR) contact events and corresponding staffing levels. The appropriate level of staffing, based on real-time and historical context to meet demand for calls, emails, messages, and other contact or servicing can be calculated without overstaffing.

Abstract: An object is to make it possible to accurately detect abnormality of event data. A training unit (105) trains a parameter of a model based on a plurality of event series that are event data in a time series and labels that indicate abnormality or normality with respect to event data of each of the plurality of event series, the model outputting a degree of abnormality of a target event series when the target event series is input, the target event series being an event series of which the degree of abnormality is to be predicted, the parameter being trained to optimize an objective function that represents a relationship between a probability of occurrence of an event at each time point in the time series and a degree of abnormality of each of the plurality of event series.

Abstract: Ideographic contrastive autoencoder for large language model fine-tuning is disclosed, including: obtaining a set of user activities according to a specified task; obtaining respective sets of input features from the set of user activities; using an encoder network of an autoencoder to encode the respective sets of input features into a set of words; prompting a machine learning model to perform the specified task using the set of words, wherein the machine learning model has been fine-tuned using a custom lexicographical vocabulary associated with the autoencoder; and presenting, at a user interface, a message determined based at least in part on an output result from the machine learning model.

Abstract: One embodiment provides a method, including: providing, from the central server to a machine-learning model, a training set of samples having known values for at least one target protected attribute, wherein the training set includes a first set of samples having a first value for the at least one target protected attribute and a second set of samples having a second value for the at least one target protected attribute; receiving, at the central server from the machine-learning model, an output classification for each of the samples within the training set of samples; and generating, at the central server using the output classification, a set of rules delineating a region within the machine-learning model as discriminatory, wherein the region includes a classification region where the machine-learning model classifies received samples differently based upon a value of the at least one protected attribute.

Abstract: A system and related methods for generating class-specific data are disclosed. The data belong to an input space with an unknown initial probability distribution and a known classification scheme. From a relatively small, unbalanced dataset of samples with respect to the classification scheme in the input space, the system is programmed to learn a series of invertible transformations from the input space to a target space, a target probability distribution for the samples in the target space, and a trainable parameter probability distribution for each parameter of the target probability distribution to represent uncertainty information related to the target probability distribution. The system is programmed to further identify how to sample from each parameter probability distribution, which determine how to sample from the target probability distribution, to generate samples in the input space that are more likely to belong to specific classes.

Abstract: The invention relates to a computer-implemented method (100) for configuring a neural network model, wherein the method comprises the following steps: providing (102) a neural network model; splitting (104) the neural network model into a first portion and a second portion, the second portion comprising a first head for classifying a first type of classification data and a second head for classifying the second type of classification data; pre-processing (106), in a training phase, the second type of classification data in the first portion, processing (108) the pre-processed second type of classification data in the first and second heads and determining a first result of the processing of first type of classification data in the first head and a second result of the processing of first type of classification data in the second head; calculating (110) the consistency between the first result and the second result; and configuring (112) the neural network model by updating a value of at least one parameter of

Abstract: Features are used to train one or more ML models in a modelling layer. In a feature selection layer, each generated ML model is analyzed to determine, for each input feature, a degree of importance of the feature on the results generated by the ML model. Features with low importance are identified and the information is propagated backward to the data source and feature engineering layers. In response, the data source and feature engineering layers refrain from gathering or generating the unimportant features. Based on a confidence measure of the determination that each feature is important or unimportant, a number of periods between reevaluation of the feature importance is determined. After the number of periods has elapsed, a removed feature is restored to the pipeline.

Abstract: Managing and applying human resources data comprising aggregating employee transaction data for an organization. A number of human resources-related attributes are evaluated across heterogeneous transaction data. The employee transaction data is classified via statistical machine learning into a number of normalized codes according to the human resources-related attributes, a user interface is presented to adjust a number of organizational operating procedures according to the normalized codes.

Abstract: A neural network processing method, comprising the following steps: obtaining a model dataset and model structure parameters of an original network (S100); obtaining an operational attribute of each compute node in the original network; operating the original network according to the model dataset and the model structure parameters of the original network and the operational attribute of each compute node, to obtain an instruction corresponding to each compute node in the original network (S200); and if the operational attribute of the current compute node is a first operational attribute, storing a network weight and the instruction corresponding to the current compute node into a first non-volatile memory, so as to obtain a first offline model corresponding to the original network (S300). Further provided are a computer system and a storage medium.

Abstract: A computerized method includes receiving a dialog session. The dialog session comprises a set of new inbound messages. The method feeds the dialog session into tokenizer. The method, with the tokenizer, generates a set of tokens by breaking the new inbound messages into a sequence of tokens. The method provides the tokens to a DAG frame labeler cascade. With the DAG frame labeler cascade, the method uses a sequence of tokens to generate a set of token labels. The method passes the token labels and tokens to an entity interpreter. With the entity interpreter, the method generates a DAG frame. With the DAG frame, the method outputs a structured information from a multiturn dialogue.