The Earth Mover’s Distance is a highly discriminative metric for measuring distance between probability distributions that has been applied successfully in various fields.
Working with IBM Research, RPI has created a first-of-its-kind, six-week credit-bearing course in Mandarin taught in the school’s Cognitive and Immersive Systems Laboratory.
IBM researchers, along with collaborators at the Universidade de Santiago de Compostela and ExxonMobil, reported in the peer-review journal Science that they have been able to resolve with unprecedented resolution the structural changes of individual molecules upon charging.
For the rapid and mobile fingerprinting of beverages and other liquids less fit for ingestion, our team at IBM Research is currently developing Hypertaste, an electronic, AI-assisted tongue that draws inspiration from the way humans taste things.
IBM cloud researchers released version 1.0.0 of OpenAPI-to-GraphQL, a library to auto-generate GraphQL wrappers for existing REST(-like) APIs. In contrast to other libraries, OASGraph is data-centric, understands swaggers and Open API Specification (OpenAPI 3.0.0) files, sanitizes / de-sanitizes parts of REST APIs not compatible with GraphQL, and makes use of OpenAPI 3.0.0 features like links to generate more usable GraphQL interfaces.
IBM researchers and geoscientists from Eni, a leading global energy company, are building an augmented intelligence platform based on AI called cognitive discovery to support Eni's decision-making during the initial stages of hydrocarbon exploration, which naturally occur in crude oil.
At CVPR 2019, IBM researchers introduce techniques to interpret visually descriptive language to generate compositional scene representations from textual descriptions.
At CVPR 2019, IBM researchers introduce an improved method to bridge the semantic gap between visual scenes and language to produce diverse, creative and human-like captions.
Data augmentation is one of the leading methods to tackle the problem of few-shot learning, but current synthesis approaches only address the scenario of a single label per image, when in reality real life images may contain multiple objects. The IBM team came up with a novel technique for synthesizing samples with multiple labels.
Our team of IBM researchers published research in Radiology around a new AI model that can predict the development of malignant breast cancer in patients within the year, at rates comparable to human radiologists.
Deep neural networks have demonstrated good results for few-shot learning. However, very few works have investigated the problem of few-shot object detection. A team of IBM researchers developed a novel approach for Distance Metric Learning (DML).
New techniques make fine tuning an AI model more efficient when doing transfer learning