Results

An evaluation framework that supports optimization of machine learning deployments for inference performance.

An approach to detect erroneous predictions or problematic inputs in neural networks.

A data quality dashboard for the monitoring and management of large volumes of time-series data generated by sensors and smart meters.

This novel design brings significant enhancements to the field of data science, particularly in the areas of data profiling, validation, error detection, and correction.

A processing workflow for images which involves facial anonymization to offer a privacy-friendly AI model generation process.

A Toolkit to capture information related to the ML models, such as intended use cases and the limitation of the ML model.

The ML lineage is a framework to holistically capture and connect the required information about ML model development and operations. 

Mosquito is a novel data cleaning technology used for cleaning data extracted from invoice PDFs.

A portable, cloud agnostic ML/AI platform that enables the creation and execution of ML/AI services.

Discrepancy Scaling is a fast and accurate deep-learning based unsupervised anomaly detection and localization method for image data.

A validation tool that can be used to evaluate and assess the accuracy, reliability and performance of pose estimation models.