Techniques are disclosed for generating a sequence of symbols based on input data for a neuro-linguistic model. The model may be used by a behavior recognition system to analyze the input data. A mapper component of a neuro-linguistic module in the behavior recognition system receives one or more normalized vectors generated from the input data. The mapper component generates one or more clusters based on a statistical distribution of the normalized vectors. The mapper component evaluates statistics and identifies statistically relevant clusters. The mapper component assigns a distinct symbol to each of the identified clusters.

A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.

Various embodiments are generally directed to techniques for generating synthetic data with simulated handwriting, such as for training or evaluating a computer vision process, for instance. Some embodiments are particularly directed to creating simulated handwriting based on input text. For example, attributes of various glyphs included in typefaces stored in a vectorized graphics format may be randomized to produce randomized glyphs. The randomized glyphs may then be used to replace glyphs in an input text to generate simulated handwriting for the input text. In some embodiments, simulated handwriting may be overlaid with a background image to produce a synthetic handwriting image. In some such embodiments, noise may be introduced into the synthetic handwriting image to generate synthetic data comprising the simulated handwriting. In one embodiment, the synthetic data may simulate a handwritten check that is used to train or evaluate an optical character recognition process.

A device, method, and non-transitory computer readable medium are described. The method includes receiving a dataset including hand written Arabic words and hand written Arabic alphabets from one or more users. The method further includes removing whitespace around alphabets in the hand written Arabic words and the hand written Arabic alphabets in the dataset. The method further includes splitting the dataset into a training set, a validation set, and a test set. The method further includes classifying one or more user datasets from the training set, the validation set, and the test set. The method further includes identifying the target user from the one or more user datasets. The identification of the target user includes a verification accuracy of the hand written Arabic words being larger than a verification accuracy threshold value.

Systems, methods, and computer-readable media are disclosed for visual labeling of training data items for training a machine learning model. Training data items may be generated for training the machine learning model. Visual labels, such as QR codes, may be created for the training data items. The creation of the training data item and the visual label may be automated. The visual labels and the training data items may be combined to obtain a labeled training data item. The labeled training data item may comprise a separator to distinguish the training data item from the visual label. The labeled training data item may be used for training and validation of the machine learning model. The machine learning model may analyze the training data item, attempt to identify the training data item, and compare the identification against the embedded label.

A method of generating a font database, and a method of training a neural network model are provided, which relate to a field of artificial intelligence, in particular to a computer vision and deep learning technology. The method of generating the font database includes: determining, by using a trained similarity comparison model, a basic font database most similar to handwriting font data of a target user in a plurality of basic font databases as a candidate font database; and adjusting, by using a trained basic font database model for generating the candidate font database, the handwriting font data of the target user, so as to obtain a target font database for the target user.

Systems, devices, methods, and computer-readable media for evaluation and visualization of machine learning data drift. A method can include receiving a series of data indicating accuracy and confidence associated with classification of respective batches of input samples, and dynamically displaying, on the GUI, a concurrent plot of the accuracy and confidence as the series of data are received.

In certain embodiments, training of a prediction model (e.g., recognition or other prediction model) may be facilitated via a training set based on one or more logos or other graphics. In some embodiments, graphics information associated with a logo or graphic (e.g., to be recognized via a recognition model) may be obtained. Media items (e.g., images, videos, etc.) may be generated based on the graphics information, where each of the media items includes (i) content other than the logo and (ii) a given representation of the logo integrated with the other content. In some embodiments, the media items may be processed via the recognition model to generate predictions (related to recognition of the logo or graphic for the media items). The recognition model may be updated based on (i) the generated predictions and (ii) corresponding reference indications (related to recognition of the logo for the media items).

Described herein is a computer-implemented method for automatic extraction of canonical data from an electronic document. The method comprises classifying a first text rectangle in an electronic document as a label and a second text rectangle as a value using a first machine learning algorithm. A first probability score of a likelihood of the first text rectangle corresponding to a first canonical category is determined using a second machine learning algorithm. A second probability score of a likelihood of the second text rectangle corresponding to a first canonical category is determined using a third machine learning algorithm. A relative spatial position of the second text rectangle relative to the first text rectangle is calculated. Based on the relative spatial position, the first probability score, and the second probability score, the first text rectangle, and the second text rectangle are classified into the first canonical category.

An adversarial image generation method, a computer device, and a computer-readable storage medium are provided. The method includes the following. A reference model classification-equivalent with a target classification model is generated according to the target classification model. A target image is obtained and an original noise for the target image is generated according to the reference model. A first noise and the original noise are input into an adversarial model and a second noise corresponding to the first noise is output when the adversarial model meets a convergence condition, where the second noise enhances an information entropy of the original noise. An enhanced noise image corresponding to the target image is generated according to the second noise and the target image, where a classification accuracy of the enhanced noise image in the target classification model is less than a classification accuracy of the target image in the target classification model.