Abstract: Embodiments of the present disclosure provide for providing performance optimization predictions related to an entity dataset. Such embodiments may include selecting a candidate machine learning model from a plurality of candidate machine learning models based at least in part on (i) a data profile for an entity dataset associated with an entity identifier and (ii) a predefined model profile associated with the candidate machine learning model. Such embodiments may additionally or alternatively include generating a candidate feature set by modifying a predefined feature set for the candidate machine learning model based at least in part on the data profile associated with the entity identifier. Such embodiments may additionally or alternatively include generating one or more performance optimization data objects by applying the candidate machine learning model to the candidate feature set based at least in part on an objective rules set for the entity identifier.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a policy neural network for use in controlling a real-world agent in a real-world environment. One of the methods includes training the policy neural network by optimizing a first task-specific objective that measures a performance of the policy neural network in controlling a simulated version of the real-world agent; and then training the policy neural network by jointly optimizing (i) a self-supervised objective that measures at least a performance of internal representations generated by the policy neural network on a self-supervised task performed on real-world data and (ii) a second task-specific objective that measures the performance of the policy neural network in controlling the simulated version of the real-world agent.

Abstract: An apparatus and method for model optimization. is disclosed. The apparatus comprises at least a processor and a memory communicatively connected to the at least a processor. The memory instructs the processor to generate a positive feedback function of an optimal measurement, wherein generating the positive feedback function further comprises identifying, using an optimal machine-learning model, a first set of parameter changes to a subsystem corresponding to the optimal measurement, and generate a negative feedback function of the suboptimal measurement, wherein generating the negative feedback function comprises identifying, using a suboptimal machine-learning model, a second set of parameter changes to a subsystem corresponding to the suboptimal measurement.

Abstract: Systems and methods for using machine learning to extract data from electronic communications are disclosed. According to certain aspects, a machine learning model is trained on a set of tasks using a set of training data. An electronic communication indicating a purchase of a product and/or service is processed to generate augmented text that is input into the machine learning model. After analyzing the augmented text, the machine learning model outputs a set of predicted values for a set of defined categories, which an entity may use for various purposes such as to apply digital rewards to user accounts.

Abstract: A system and method are disclosed for providing an artificial intelligence platform. An example method includes examining part of a global neural network to locate a split layer in the global neural network, creating an equivalent model to the part of the global neural network of a same size but having opposite operations, generating smashed data based on an operation on input data by the part of the global neural network, training the equivalent model by inputting the smashed data to generate a second a mirrored copy of the input data, quantifying a distance between the input data and the second generated set of mirrored data to yield a value and, when the value is below a threshold, determining that a current location of the split layer in the global neural network is safe for a training process.

Abstract: Systems, methods, apparatuses, and computer program products for determining and/or applying optimal configurations in cognitive autonomous networks (CANs) are provided.

Abstract: Techniques are disclosed for facilitating the tuning of hyperparameter values during the development of machine learning (ML) models using visual analytics in a data science platform. In an example embodiment, a computer-implemented data science platform is configured to generate, and display to a user, interactive visualizations that dynamically change in response to user interaction. Using the introduced technique, a user can, for example, 1) tune hyperparameters through an iterative process using visual analytics to gain and use insights into how certain hyperparameters affect model performance and convergence, 2) leverage automation and recommendations along this process to optimize the tuning given available resources, 3) collaborate with peers, and 4) view costs associated with executing experiments during the tuning process.

Abstract: Systems and methods for routing in mixture-of-expert models. In some aspects of the technology, a transformer may have at least one Mixture-of-Experts (“MoE”) layer in each of its encoder and decoder, with the at least one MoE layer of the encoder having a learned gating function configured to route each token of a task to two or more selected expert feed-forward networks, and the at least one MoE layer of the decoder having a learned gating function configured to route each task to two or more selected expert feed-forward networks.

Abstract: A “Content Optimizer” applies a machine-learned relevancy model to predict levels of interest for segments of arbitrary content. Arbitrary content includes, but is not limited to, any combination of documents including text, charts, images, speech, etc. Various automated reports and suggestions for “reformatting” segments to modify the predicted levels of interest may then be presented. Similarly, the Content Optimizer applies a machine-learned comprehension model to predict what a human audience is likely to understand (e.g., a “comprehension prediction”) from the arbitrary content. Various automated reports and suggestions for “reformatting” segments to modify the comprehension prediction may then be presented.

Abstract: A method, a computer system, and a computer program product for a shiftleft topology construction is provided. Embodiments of the present invention may include collecting datasets. Embodiments of the present invention may include extracting topological entities from the datasets. Embodiments of the present invention may include correlating a plurality of data from the topological entities. Embodiments of the present invention may include mapping the topological entities. Embodiments of the present invention may include marking entry points for a plurality of subgraphs of the topological entities. Embodiments of the present invention may include constructing a topology graph.

Abstract: Systems, computer-implemented methods, and computer program products that facilitate temporalizing and/or spatializing a machine learning and/or artificial intelligence network are provided. In various embodiments, a processor can combine output data from different layers of an artificial neural network trained on static image data. In various embodiments, the processor can employ the artificial neural network to infer an outcome from an image instance in a sequence of images based on combined output data from the different layers of the artificial neural network.

Abstract: Embodiments of the present disclosure provide a method and apparatus for performing a structured extraction on a text, a device and a storage medium. The method may include: performing a text detection on an entity text image to obtain a position and content of a text line of the entity text image; extracting multivariate information of the text line based on the position and the content of the text line; performing a feature fusion on the multivariate information of the text line to obtain a multimodal fusion feature of the text line; performing category and relationship reasoning based on the multimodal fusion feature of the text line to obtain a category and a relationship probability matrix of the text line; and constructing structured information of the entity text image based on the category and the relationship probability matrix of the text line.

Abstract: Embodiments of the present invention provide the use of a conditional Generative Adversarial Network (GAN) to simultaneously correct and downscale (super-resolve) global ensemble weather or climate forecasts. Specifically, a generator deep neural network (G-DNN) in the cGAN comprises a corrector DNN (C-DNN) followed by a super-resolver DNN (SR-DNN). The C-DNN bias-corrects coarse, global meteorological forecasts, taking into account other relevant contextual meteorological fields. The SR-DNN downscales bias-corrected C-DNN output into G-DNN output at a higher target spatial resolution. The GAN is trained in three stages: C-DNN training, SR-DNN training, and overall GAN training, each using separate loss functions. Embodiments of the present invention significantly outperform an interpolation baseline, and approach the performance of operational regional high-resolution forecast models across an array of established probabilistic metrics.

Abstract: A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a strict partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing an area attention layer in a neural network system. The area attention layer area implements a way for a neural network model to attend to areas in the memory, where each area contains a group of items that are structurally adjacent.

Abstract: Provided is a machine learning device and method that enables machine learning of labeling, in which a plurality of labels are attached to volume data at one effort with excellent accuracy, using training data having label attachment mixed therein. A probability calculation unit (14) calculates a value (soft label) indicating a likelihood of labeling of a class Ci for each voxel of a second slice image by means of a learned teacher model (13a). A detection unit (15) detects “bronchus” and “blood vessel” for the voxels of the second slice image using a known method, such as a region expansion method and performs labeling of “bronchus” and “blood vessel”. A correction probability setting unit (16) replaces the soft label with a hard label of “bronchus” or “blood vessel” detected by the detection unit (15). A distillation unit (17) performs distillation of a student model (18a) from the teacher model (13a) using the soft label after correction by means of the correction probability setting unit (16).

Abstract: Behavioral characteristics of at least a first machine component are monitored. A model that represents machine-to-machine interactions between at least the first machine component and at least a further machine component is generated. Using the monitored behavioral characteristics and the generated model, an incongruity of a behavior of at least the first machine component and the machine-to-machine interactions is computed, where the incongruity is predicted based on determining a discordance between an expectation of the system and the behavior and the machine-to-machine interactions, and wherein the predicting is performed without using a previously built normative rule of behavior and machine-to-machine interactions.

Abstract: A search engine server includes a communication interface through which to receive a multi-modal query from a browser of a client device, the multi-modal query including at least a first image of an item. A processing device, coupled to the communication interface, is to: execute a neural network (NN) regressor model on the first image to identify a plurality of second items that are similar to and compatible with the item depicted in the first image, wherein a set of images correspond to the plurality of second items; generate structured text that explains, within one of a phrase or a sentence, why the set of images are relevant to the item; and return, to the browser of the client device via the communication interface, a set of search results comprising the set of images and the structured text.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning from delayed outcomes using neural networks. One of the methods includes receiving an input observation; generating, from the input observation, an output label distribution over possible labels for the input observation at a final time, comprising: processing the input observation using a first neural network configured to process the input observation to generate a distribution over possible values for an intermediate indicator at a first time earlier than the final time; generating, from the distribution, an input value for the intermediate indicator; and processing the input value for the intermediate indicator using a second neural network configured to process the input value for the intermediate indicator to determine the output label distribution over possible values for the input observation at the final time; and providing an output derived from the output label distribution.

Abstract: Based on a normal model, it is detected whether or not an event signal of a computer system is anomalous. In parallel with the normal-model-based anomaly detection, it is detected based on a rule whether or not the event signal is anomalous. Then, a final anomaly detection result is generated by performing comprehensive determination based on detection results of the normal-model-based anomaly detection and the rule-based anomaly detection.