The present disclosure is related to systems and methods for processing speech dialogue. The method includes obtaining target speech dialogue data. The method includes obtaining a text vector representation sequence, a phonetic symbol vector representation sequence, and a role vector representation sequence by performing a vector transformation on the target speech dialogue data based on a text embedding model, a phonetic symbol embedding model, and a role embedding model, respectively. The method includes determining a representation vector corresponding to the target speech dialogue data by inputting the text vector representation sequence, the phonetic symbol vector representation sequence, and the role vector representation sequence into a trained speech dialogue coding model. The method includes determining a summary of the target speech dialogue data by inputting the representation vector into a classification model.

Disclosed herein are a learning-based three-dimensional (3D) model creation apparatus and method. A method for operating a learning-based 3D model creation apparatus includes generating multi-view feature images using supervised learning, creating a three-dimensional (3D) mesh model using a point cloud corresponding to the multi-view feature images and a feature image representing internal shape information, generating a texture map by projecting the 3D mesh model into three viewpoint images that are input, and creating a 3D model using the texture map.

A system and method for training set of images in which objects of a particular class are identified and using the training set train a model to identify other objects of the class and a candidate object. Calculating a feature vector describing candidate object identified in an image and further calculating a score regarding the similarity between the feature vector and another feature vector describing the identified objects in the training set, and provided that the score passes a predefined threshold, adding the image to the training set, and using the augmented training set, retrain the model.

An object is to make it possible to train an image recognizer by efficiently using training data that does not include label information. A determination unit 180 causes repeated execution of the followings. A feature representation model for extracting feature vectors of pixels is trained such that an objective function is minimized, the objective function being expressed as a function that includes a value that is based on a difference between a distance between feature vectors of pixels labeled with a positive example label and a distance between a feature vector of a pixel labeled with the positive example label and a feature vector of an unlabeled pixel, and a value that is based on a difference between a distance between a feature vector of a pixel labeled with the positive example label and a feature vector of an unlabeled pixel and a distance between a feature vector of a pixel labeled with the positive example label and a feature vector of a pixel labeled with a negative example label, and based on a distribution of feature vectors corresponding to the positive example label, a predetermined number of labels are given based on the likelihood that each unlabeled pixel is a positive example.

A computer-implemented method for classification of data by a machine learning system using a logic constraint for reducing a data labeling requirement. The computer-implemented method includes: generating a first embedding space from a first partially labeled training data set, wherein in the first embedding space, content-wise related training data of the first partially labeled training data are clustered together, determining at least two clusters in the first embedding space formed from the first partially labeled training data, and training a machine learning model based, at least in part, on a second partially labeled training data set and the at least two clusters, wherein the at least two clusters are used as training constraints.

A computing device classifies unclassified observations. A first batch of unclassified observation vectors and a first batch of classified observation vectors are selected. A prior regularization error value and a decoder reconstruction error value are computed. A first batch of noise observation vectors is generated. An evidence lower bound (ELBO) value is computed. A gradient of an encoder neural network model is computed, and the ELBO value is updated. A decoder neural network model and an encoder neural network model are updated. The decoder neural network model is trained. The target variable value is determined for each observation vector of the unclassified observation vectors based on an output of the trained decoder neural network model. The target variable value is output.

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.

Aspects of the present invention disclose a method, computer program product, and system for pre-training a neural network. The method extracting features of data set received from a source, the data set includes labelled data and unlabeled data. Generating a plurality of data clusters from instances of data in the data set, the data clusters are weighted according to a respective number of similar instances of labeled data and unlabeled data within a respective data cluster. Determining a data label indicating a data class that corresponds to labeled data within a data cluster of the generated plurality of data clusters. Applying the determined data label to unlabeled data within the data cluster of the generated plurality of data clusters. In response to applying the determined data label to unlabeled data within the data cluster of the generated plurality of data clusters, deploying the data cluster to a neural network.

System, methods, and other embodiments described herein relate to self-supervised training of a depth model for monocular depth estimation. In one embodiment, a method includes processing a first image of a pair according to the depth model to generate a depth map. The method includes processing the first image and a second image of the pair according to a pose model to generate a transformation that defines a relationship between the pair. The pair of images are separate frames depicting a scene of a monocular video. The method includes generating a monocular loss and a pose loss, the pose loss including at least a velocity component that accounts for motion of a camera between the training images. The method includes updating the pose model according to the pose loss and the depth model according to the monocular loss to improve scale awareness of the depth model in producing depth estimates.

According to an embodiment, an information processing device include: one or more processors. The processors input data based on input data including first input data belonging to a first domain and second input data belonging to a second domain different from the first domain, to a first model, and acquire first output data indicating an execution result of a first task with the first model. The processors input data based on the input data to a second model, and acquire second output data indicating an execution result of a second task with the second model. The processors convert the first output data into first conversion data expressed in a form of an execution result of the second task. The processors generate supervised data of the second model for the first input data, based on the first conversion data and the second output data.