Abstract: A system for providing performance optimization for a software solution may scan multiple predefined levels of the software solution to extract corresponding metadata information from each of the multiple predefined levels. The system may store the extracted corresponding metadata information pertaining to standard parameters associated with performance of the software solution. The system may determine a standard score based on a plurality of attributes of the extracted corresponding metadata information, optimize the determined standard score based on training data received from a learning model, and generate an insight information comprising information related to determined rule violations and of evaluation steps involved in determining the determined standard score.

Abstract: Systems and methods of the present disclosure may receive, from a user computing device, a user-provided data record query including a natural language request for information associated with one or more data sources. User persona attributes of the user may be determined, such as a user role or security parameters or both. Based on the user persona attributes a context query may be generated to obtain context attributes associated with the user-provided query. The natural language request and the context attributes are input into the model orchestration large language model (LLM) to output instructions to machine learning (ML) agents based on the context attributes. The ML agents output responses associated with the user-provided data record query based on the instructions, and the responses are input into the model orchestration LLM to output to the user computing device a natural language response based on the context attributes.

Abstract: A method for using knowledge infusion for robust and transferable machine learning models includes receiving a plurality of adaptive and programmable knowledge functions comprising a plurality of strong functions and a plurality of weak functions. A knowledge model is generated based on the plurality of strong functions and the plurality of weak functions. A machine learning model is trained based on the generated knowledge model.

Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing, by a bidirectional Long Short-Term Memory (LSTM) with a multi-head attention mechanism, a dataset including a plurality of pairs each formed from a given one of a plurality of input text structures and given one of a plurality of style labels for the plurality of input text structures. The method further includes training the bidirectional LSTM as an encoder to disentangle a sequential text input into disentangled representations comprising a content embedding and a style embedding based on a subset of the dataset. The method also includes training a unidirectional LSTM as a decoder to generate a next text structure prediction for the sequential text input based on previously generated text structure information and a current word, from a disentangled representation with the content embedding and the style embedding.

Abstract: A computational block configured to perform an inference task by applying a plurality of low resource computing operations to a binary input feature tensor to generate an integer feature tensor that is equivalent to an output of multiplication and accumulation operations performed in respect of a ternary weight tensor and the binary input feature tensor; and performing a comparison operation between the generated integer feature tensor and a comparison threshold to generate a binary output feature tensor.

Abstract: An automatic agent may be trained using reinforcement learning. A secret task may be obtained for a simulated user, and the secret task may be unknown to the automatic agent. At least one instruction to complete the secret task may be obtained from the simulated user according to at least one RL policy. At least one action may be generated by the automatic agent based on the at least one instruction and the at least one RL policy. Rewards may be determined for the simulated user and the automatic agent in response to determining that the at least one action successfully completes the secret task. The at least one RL policy may be adjusted based on the determined rewards.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes a plurality of workers, wherein each worker is configured to operate independently of each other worker, and wherein each worker is associated with a respective actor that interacts with a respective replica of the environment during the training of the deep neural network.

Abstract: Systems and methods are disclosed which allow mobile devices, and other resource constrained applications, to more efficiently and effectively utilize deep learning neural networks using only (or primarily) local resources. These systems and methods take the dynamics of runtime resources into account to enable resource-aware, multi-tenant on-device deep learning for artificial intelligence functions for use in tasks like mobile vision systems. The multi-capacity framework enables deep learning models to offer flexible resource-accuracy trade-offs and other similar balancing of performance and resources consumed. At runtime, various systems disclosed herein may dynamically select the optimal resource-accuracy trade-off for each deep learning model to fit the model's resource demand to the system's available runtime resources and the needs of the task being performed by the model.

Abstract: In one embodiment, a device maintains a metamodel that describes a monitored system. The metamodel comprises a plurality of layers ranging from a sub-symbolic space to a symbolic space. The device tracks updates to the metamodel over time. The device updates the metamodel based in part on sub-symbolic time series data generated by the monitored system. The device receives, from a learning agent, a request for the updates to a particular layer of the metamodel associated with a specified time period. The device provides, to the learning agent, data indicative of one or more updates to the particular layer of the metamodel associated with the specified time period.

Abstract: Examples of methods performed by an electronic device are described. In some examples of the methods, a machine learning model is trained based on a plurality of interaction events and a corresponding plurality of images. In an example, each of the plurality of interaction events corresponds to one of a plurality of displays. In some examples of the methods, a display is selected of the plurality of displays based on the machine learning model. In an example, an object is presented on the display.

Abstract: Techniques regarding qubit coupling structures that enable RIP gates are provided. For example, one or more embodiments described herein can comprise an apparatus that can include a coupling structure coupled to a first qubit and a second qubit. The coupling structure can have a plurality of coupling pathways. A coupling pathway from the plurality of coupling pathways can be a resonator. Also, the first qubit can be coupled to a first end of the resonator, and the second qubit can be coupled to a point along a length of the resonator.

Abstract: Disclosed examples include after a first tuning of hyperparameters in a hyperparameter space, selecting first hyperparameter values for respective ones of the hyperparameters; generating a polygonal shaped failure region in the hyperparameter space based on the first hyperparameter values; setting the first hyperparameter values to failure before a second tuning of the hyperparameters; and selecting second hyperparameter values for the respective ones of the hyperparameters in a second tuning region after the second tuning of the hyperparameters in the second tuning region, the second tuning region separate from the polygonal shaped failure region.

Abstract: A method for analyzing a simulation of the execution of a quantum circuit comprises: a step of post-selecting (S2) one or more particular values of one or more qubits at one or more steps of the simulation, a step of retrieving (S5), by an iterator (7), all or some of the quantum states of the quantum state vector(s) derived from the post-selection(s) of qubits, a step of analyzing (S6) the part of the simulation that corresponds to the post-selection(s) of qubits and to the quantum state vector(s) retrieved.

Abstract: Techniques are described for performing active surveillance and learning for machine learning (ML) model authoring and deployment workflows. In an embodiment, a method comprises applying, by a system comprising a processor, a primary ML model trained on a training dataset to data samples excluded from the training dataset to generate inferences based on the data samples. The method further comprises employing, by the system, one or more active surveillance techniques to regulate performance of the primary ML model in association with the applying, wherein the one or more active surveillance techniques comprise at least one of, performing a model scope evaluation of the primary ML model relative to the data samples or using a domain adapted version of the primary ML model to generate the inferences.

Abstract: An information processing device according to the present invention includes: a memory; and at least one processor coupled to the memory. The processor performs operations. The operations includes: extracting a feature of a period or a frequency in a plurality of pieces of time-series data acquired by measuring an object; classifying the pieces of time-series data into a group related to the feature; generating, for each of the groups, a model that represents a relationship among the pieces of time-series data classified into the group; and selecting the model in which strength of the relationship satisfies a predetermined condition.

Abstract: Examples herein propose operating redundant ML models which have been trained using a boosting technique that considers hardware faults. The embodiments herein describe performing an evaluation process where the performance of a first ML model is measured in the presence of a hardware fault. The errors introduced by the hardware fault can then be used to train a second ML model. In one embodiment, a second evaluation process is performed where the combined performance of both the first and second trained ML models is measured in the presence of a hardware fault. The resulting errors can then be used when training a third ML model. In this manner, the three trained ML models are trained to be error aware. As a result, during operation, if a hardware fault occurs, the three ML models have better performance relative to three ML models that where not trained to be error aware.

Abstract: Techniques for implementing unsupervised anomaly detection by self-prediction are provided. In one set of embodiments, a computer system can receive an unlabeled training data set comprising a plurality of unlabeled data instances, where each unlabeled data instance includes values for a plurality of features. The computer system can further train, for each feature in the plurality of features, a supervised machine learning (ML) model using a labeled training data set derived from the unlabeled training data set, receive a query data instance, and generate a self-prediction vector using at least a portion of the trained supervised ML models and the query data instance, where the self-prediction vector indicates what the query data instance should look like if it were normal. The computer system can then generate an anomaly score for the query data instance based on the self-prediction vector and the query data instance.

Abstract: A bearing fault diagnosis method based on a fuzzy broad learning mode includes steps of constructing an initial fuzzy broad learning model based on a broad learning system and a fuzzy system, training the initial fuzzy broad learning model through training set data to obtain a target fuzzy broad learning model. The training set data includes a plurality of bearing vibration signal data with a fault type label; and a membership value of a bearing vibration signal data to be tested is calculated by the target fuzzy broad learning model. A fault type of the bearing to be tested is determined based on the membership value. The bearing fault diagnosis method reduces learning time. When determining the fault type of the bearing to be tested by the target fuzzy broad learning model, it has strong robustness, fast diagnosis speed and high fault diagnosis accuracy.

Abstract: Techniques for classifier generalization in a supervised learning process using input encoding are provided. In one aspect, a method for classification generalization includes: encoding original input features from at least one input sample {right arrow over (x)}S with a uniquely decodable code using an encoder E(?) to produce encoded input features E({right arrow over (x)}S), wherein the at least one input sample {right arrow over (x)}S comprises uncoded input features; feeding the uncoded input features and the encoded input features E({right arrow over (x)}S) to a base model to build an encoded model; and learning a classification function {tilde over (C)}E(?) using the encoded model, wherein the classification function {tilde over (C)}E(?) learned using the encoded model is more general than that learned using the uncoded input features alone.

Abstract: An artificial intelligence (AI) parameter configuration method for a racing AI model performed by an AI parameter configuration device is provided. A first parameter set including m sets of AI parameters is obtained. Each of the m sets of AI parameters is used by the racing AI model to travel on a track. The racing AI model is controlled to undergo an adaptation degree test according to each of the m sets of AI parameters to obtain m adaptation degrees. The m adaptation degrees are positively correlated with travel distances of the racing AI model on the track according to the m sets of AI parameters. A second parameter set is generated according to the first parameter set in a case that all the m adaptation degrees are less than an adaptation degree threshold. In a case that a target adaptation degree in the m adaptation degrees is greater than the adaptation degree threshold, an AI parameter corresponding to the target adaptation degree is configured as a target AI parameter.