In Artificial Intelligence, Machine Learning technologies allow us to define algorithms and information technology systems with the capacity to improve their performance by learning from experience. Whether we are discussing supervised learning with annotated data or semi-supervised or even unsupervised learning –without annotations or prior classifications–, or if we use techniques such as Reinforcement Learning or even Deep Learning with deep neuronal networks, our team works on how to apply these techniques to resolve real problems in businesses.
A Common Technological Approach, Different Sectors
Thanks to the current capacity for the generation, storage and transmission of Big Data, and with new Machine Learning algorithms such as Deep Learning, at Vicomtech we have successfully applied disruptive solutions in multiple sectors, such as Industry, Oil and Gas, medicine, transport, cybersecurity, energy, surveillance of critical infrastructures, services, communication and language, Internet and Media, etc.
Machine Learning Enriches Other Key Technologies
Machine Learning technologies have a direct relationship and give an enormous boost to other fundamental technologies at Vicomtech. For example, they are applied in Computer Vision for problems such as the classification of industrial defects, the prediction of dangerous situations in autonomous driving and analysis of cancer images. They are also applied in Data Intelligence to extract valuable information and findings, such as predictions based on data from machinery and industrial production sensors. Or, for example, in Speech, Dialogue and Natural Language Processing, they allow the improvement of transcription and translation systems at previously unknown levels. Machine Learning is an enabler in multiple technologies and sectors.
A couple of examples
A couple of examples will help demonstrate the applicability of Machine Learning. We have helped a large electronics company to develop Augmented Reality stations so that their operators can assemble tens of thousands of electronic components with a system which automatically learns from a few examples. We have provided a world leader in the automotive sector with a system supported by Machine Learning for the semi-automatic annotation of huge amounts of video to prepare its autonomous driving systems. We have helped a continuous process industry predict and anticipate faults in their production, based on data from their sensors and control systems, with very significant savings. These are just a few examples among many showing the relevance and applicability of Machine Learning.
- Noteworthy Projects
Towards Autonomous Defense of SDN Networks Using MuZero Based Intelligent Agents
Analysis of copernicus’ era5 climate reanalysis data as a replacement for weather station temperature measurements in machine learning models for olive phenology phase prediction
MRI to CTA Translation for Pulmonary Artery Evaluation Using CycleGANs Trained with Unpaired Data
Reliability of Supervised Machine Learning Using Synthetic Data in Health Care: Model to Preserve Privacy for Data Sharing
JMIR Medical Informatics
Knowledge-based automated planning system for StereoElectroEncephaloGraphy: a center-based scenario
Journal of Biomedical Informatics
Leverages data captured by cars to stimulate, facilitate and feed innovative products and services
Develop central coordination of ground units, innovative data models, and advanced audio and video analysis and storage
Research in the meat of the future intended for the prevention of colon cancer and dyslipemias. The best valued R&D project in all areas of the CDTI MISSIONS call