Abstract: In example embodiments, a dataset labeling software process combines diversity selection and with one or more uncertainty selection techniques in a multi-stage process that produces a labeled training dataset for training an image-based ML model. In an initial stage, diversity selection alone may be used to seed a labeled training dataset. In a subsequent stage, diversity selection may be combined with a first procedure for computing uncertainty (e.g., uncertainty selection based on ensemble learning) to build the labeled training dataset until a first stopping condition is met. Optionally, in a still further stage, diversity selection may be combined with a second, different procedure for computing uncertainty (e.g., uncertainty selection based on Monte Carlo (MC) dropout) to further build the labeled training dataset until a second stopping condition is met.

Abstract: In example embodiments, techniques are provided for customizing a ML model for a specific user absent user-coding. The techniques may provide a “black box” service to the user where the intricacies of ML model training are abstracted, and the user simply provides source data and makes high level selections. The techniques may be used with a variety of types of ML model architectures and ML Pipelines.

Abstract: In example embodiments, a semantic multimodal search function is provided in an engineering application for searching engineering documents. In an indexing phase, the application indexes a library of engineering documents to build an embedding database. For each of the engineering documents, a region detector extracts regions that each correspond to a different mode of technical or engineering data, and a set of ML models is used to generate embeddings that represent the semantic significance of technical or engineering data in each of the regions. In a query phase, the application receives search input and uses the region detector to extract regions that each correspond to a different mode of input. The application uses the ML models to generate embeddings that represent the semantic significance of input in each of the regions, and then performs a vector search between these embeddings and those in the embedding database.

Abstract: In example embodiments, techniques are provided for classifying elements of infrastructure models using a convolutional graph neural network (GNN). Graph-structured data structures are generated from infrastructure models, in which nodes represent elements and edges represent contextual relationships among elements (e.g., based on proximity, functionality, parent-child relationships, etc.). During training, the GNN learns embeddings from the nodes and edges of the graph-structured data structures, the embeddings capturing contextual clues that distinguish between elements that may share similar geometry (e.g., cross section, volume, surface area, etc.), yet serve different purposes.

Abstract: In example embodiments, techniques are provided for using machine learning to predict railroad track geometry exceedances to enable proactive maintenance. A machine learning model of a rail operational analytics application may be trained to directly output a probability of future railroad track geometry exceedances for each portion of track of a railroad. Training may be performed using all available railroad track data, and the task of selecting which data is relevant to predicting probability of railroad track geometry exceedances may be devolved to the machine learning model. Further, assumptions about the specific railroad and data characteristics may be avoided, providing the machine learning model flexibility, and allowing for dynamic changes in the problem formulation.

Abstract: In example embodiments, techniques are provided for classifying elements of infrastructure models using a convolutional graph neural network (GNN). Graph-structured data structures are generated from infrastructure models, in which nodes represent elements and edges represent contextual relationships among elements (e.g., based on proximity, functionality, parent-child relationships, etc.). During training, the GNN learns embeddings from the nodes and edges of the graph-structured data structures, the embeddings capturing contextual clues that distinguish between elements that may share similar geometry (e.g., cross section, volume, surface area, etc.), yet serve different purposes.

Abstract: In example embodiments, techniques are provided for labeling elements of an infrastructure model with classes. The techniques may be implemented by a labeling tool that uses an ML model to create element selections and provides a cycle review mode to speed review within such selections. The labeling tool may further provide for two file loading and a number of visualization schemes to speed comparison of label files and prediction files.

Abstract: In example embodiments, techniques are provided to automatically identify misclassified elements of an infrastructure model using machine learning. In a first set of embodiments, supervised machine learning is used to train one or more classification models that use different types of data describing elements (e.g., a geometric classification model that uses geometry data, a natural language processing (NLP) classification model that uses textual data, and an omniscient (Omni) classification model that uses a combination of geometry and textual data; or a single classification model that uses geometry data, textual data, and a combination of geometry and textual data). Predictions from classification models (e.g., predictions from the geometric classification model, NLP classification model and the Omni classification model) are compared to identify misclassified elements, or a prediction of misclassified elements directly produced (e.g., from the single classification model).

Abstract: In example embodiments, techniques are provided to automatically classify individual elements of an infrastructure model by training one or more machine learning algorithms on classified infrastructure models, producing a classification model that maps features to classification labels, and utilizing the classification model to classify the individual elements of the infrastructure model. The resulting classified elements may then be readily subject to analytics, for example, enabling the display of dashboards for monitoring project performance and the impact of design changes. Such techniques enable classification of elements of new infrastructure models or in updates to existing infrastructure models.

Abstract: In example embodiments, a software service may employ a neural network to learn a non-linear mapping that transforms element features into embeddings. The neural network may be trained to distribute the embeddings in multi-dimensional embedding space, such that distance between the embeddings is meaningful to the class or category classification, or property prediction, task at hand. The neural network may be trained using weakly supervised machine learning, using weakly labeled infrastructure models. Embeddings for groups may be used to determine prototypes. Elements of an infrastructure model may be classified into classes or categories, or their properties predicted, as the case may be, by finding a nearest prototype.

Abstract: In example embodiments, techniques are provided to automatically identify misclassified elements of an infrastructure model using machine learning. In a first set of embodiments, supervised machine learning is used to train one or more classification models that use different types of data describing elements (e.g., a geometric classification model that uses geometry data, a natural language processing (NLP) classification model that uses textual data, and an omniscient (Omni) classification model that uses a combination of geometry and textual data; or a single classification model that uses geometry data, textual data, and a combination of geometry and textual data). Predictions from classification models (e.g., predictions from the geometric classification model, NLP classification model and the Omni classification model) are compared to identify misclassified elements, or a prediction of misclassified elements directly produced (e.g., from the single classification model).

Abstract: In example embodiments, techniques are provided to automatically classify individual elements of an infrastructure model by training one or more machine learning algorithms on classified infrastructure models, producing a classification model that maps features to classification labels, and utilizing the classification model to classify the individual elements of the infrastructure model. The resulting classified elements may then be readily subject to analytics, for example, enabling the display of dashboards for monitoring project performance and the impact of design changes. Such techniques enable classification of elements of new infrastructure models or in updates to existing infrastructure models.

Abstract: The present relates to a spatially modulated cladding mode stripper and to an optical fiber comprising a spatially modulated cladding mode stripper. The spatially modulated cladding mode stripper comprises a series of alternating high cladding light extracting regions and low cladding light extracting regions located along a portion of a cladding to modulate extracting of cladding light therefrom.

Abstract: The present relates to a spatially modulated cladding mode stripper and to an optical fiber comprising a spatially modulated cladding mode stripper. The spatially modulated cladding mode stripper comprises a series of alternating high cladding light extracting regions and low cladding light extracting regions located along a portion of a cladding to modulate extracting of cladding light therefrom.