A method, system and computer-readable storage medium for performing a cognitive information processing operation. The cognitive information processing operation includes: receiving data from a plurality of data sources; processing the data from the plurality of data sources to provide cognitively processed insights via an augmented intelligence system, the augmented intelligence system executing on a hardware processor of an information processing system, the augmented intelligence system and the information processing system providing a cognitive computing function; performing a robustness assessment operation, the robustness assessment operation assessing robustness of the cognitive computing function, the robustness assessment operation generating a robustness score representing robustness of the cognitive computing function; and, providing the cognitively processed insights to a destination, the destination comprising a cognitive application, the cognitive application enabling a user to interact with the cognitive insights.

Methods, apparatus, systems, and articles of manufacture are disclosed to identify code semantics. An example apparatus includes processor circuitry to perform at least one of first, second, or third operations to instantiate validated repository parse circuitry to identify embedding values corresponding to validated code, syntax analysis circuitry to identify syntax information based on statistical recurrence metrics of the embedding values, bidirectional model circuitry to train a forward semantic model and a backward semantic model based on (a) semantic information corresponding to the syntax information and (b) divisional segmentation information corresponding to the syntax information, and target repository mining circuitry to generate target code model input fragments including learned syntactic information, learned semantic information, and learned divisional segmentation information, the target code model input fragments to facilitate inference with the forward semantic model and the backward semantic model.

Methods, apparatus, systems, and articles of manufacture are disclosed to identify code semantics. An example apparatus includes processor circuitry to perform at least one of first, second, or third operations to instantiate validated repository parse circuitry to identify embedding values corresponding to validated code, syntax analysis circuitry to identify syntax information based on statistical recurrence metrics of the embedding values, bidirectional model circuitry to train a forward semantic model and a backward semantic model based on (a) semantic information corresponding to the syntax information and (b) divisional segmentation information corresponding to the syntax information, and target repository mining circuitry to generate target code model input fragments including learned syntactic information, learned semantic information, and learned divisional segmentation information, the target code model input fragments to facilitate inference with the forward semantic model and the backward semantic model.

The present invention discloses system and method for processing an image. The invention processes the image by segmenting a human portrait region of the image. The invention uses ahierarchical hybrid loss module for masking the portrait region generating masked portrait region. The invention also uses data learning the masked portrait region.

The present invention discloses system and method for processing an image. The invention processes the image by segmenting a human portrait region of the image. The invention uses ahierarchical hybrid loss module for masking the portrait region generating masked portrait region. The invention also uses data learning the masked portrait region.

Embodiments improve data quality using artificial intelligence. Incoming data that includes a plurality of rows of data and a trained neural network that is configured to predict a data category for the incoming data can be received, where the neural network has been trained with training data including training features, and the training data includes labeled data categories. The incoming data can be processed, where the processing extracts features about the plurality of rows of data to generate metadata profiles that represent the incoming data. Using the trained neural network, a data category for the incoming data can be predicted, where the prediction is based on the generated metadata profiles.

Embodiments improve data quality using artificial intelligence. Incoming data that includes a plurality of rows of data and a trained neural network that is configured to predict a data category for the incoming data can be received, where the neural network has been trained with training data including training features, and the training data includes labeled data categories. The incoming data can be processed, where the processing extracts features about the plurality of rows of data to generate metadata profiles that represent the incoming data. Using the trained neural network, a data category for the incoming data can be predicted, where the prediction is based on the generated metadata profiles.

A method and an apparatus for training a transferable vision transformer (TVT) for unsupervised domain adaption (UDA) in heterogeneous devices are provided. The method includes that a heterogeneous device including one or more graphic processing units (GPUs) loads multiple patches into the TVT which includes a transferability adaption module (TAM). Furthermore, a patch-level domain discriminator in the TAM assigns weights to the multiple patches and determines one or more transferable patches based on the weights. Moreover, the heterogeneous device generates a transferable attention output for an attention module in the TAM based on the one or more transferable patches.

[Problem] To shorten the processing time without performing complicated processing during image reading. [Solution] The present disclosure provides an image processing apparatus that includes: a dividing unit that divides a detection region for detecting a feature value of an image into a plurality of regions; a decimation processing unit that performs a decimation process on a pixel value for each of the regions; and a histogram calculating unit that interpolates a pixel value having undergone the decimation process to calculate a histogram of pixel values of the regions. With this configuration, it is possible to shorten the processing time without performing complicated processing during image reading.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection policy neural network, wherein the action selection policy neural network is configured to process an observation characterizing a state of an environment to generate an action selection policy output, wherein the action selection policy output is used to select an action to be performed by an agent interacting with an environment. In one aspect, a method comprises: obtaining an observation characterizing a state of the environment subsequent to the agent performing a selected action; generating a latent representation of the observation; processing the latent representation of the observation using a discriminator neural network to generate an imitation score; determining a reward from the imitation score; and adjusting the current values of the action selection policy neural network parameters based on the reward using a reinforcement learning training technique.