Меню
КартаВръзкиТемиБългарияНощта (K-TRIO)Мария Склодовска-КюриЗа ученициЗа учителиМетодологияИзненадай ме
H2020Обмен на изследователи2017–2022

LAMBDA · Learning and Analysing Massive / Big complex Data

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период
2017-03-01 → 2022-08-31
Финансиране от ЕС
337 500 €
Участници
7
Схема
MSCA-RISE

Линиите свързват координатора с партньорите.

Накратко на български

Методите за машинно обучение се прилагат за анализ на сложни данни, като например 3D форми в медицината или поведението на шофьорите. Това помага за създаването на софтуер, който обработва огромни масиви от информация за нуждите на индустрията.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

Learning and Analysing Massive / Big complex Data

LAMBDA aimed at transferring game changing technologies to the European industry in critical areas of Machine learning. Based on recent algorithmic breakthroughs, we adapted sophisticated methods to targeted industries to help turn cutting edge tools into innovative software products or processes, tailored to real-world issues. LAMBDA focused on two distinct application domains: 3D shape analysis and unstructured data mining. They share challenging features such as inherent complexity in modeling the data, high dimensionality which raises the issue of curse of dimensionality, and the need to address such datasets at a massive scale. 3D shape analysis is an important current problem in medicine, biology, as well as mechanical engineering and simulation. Given the huge success of manipulating language and speech (one dimensional) as well as images (2D), it is a natural next step to develop technology for 3D data. Our second domain of application is handling unstructured (such as driving-insurance) data so as to model and monitor driving behaviour, detect dangerous road segments, as well as forecast time of arrival. For each application domain the consortium included a significant industrial stakeholder within EU. LAMBDA was characterised by a unique blend of theoretically rigorous and geometrically inclined methods, thus supporting a strong aspect of interdisciplinarity between Theory of Algorithms and Machine Learning. This was supported by software development, ranging from prototype implementations to software ready to be integrated in respective libraries. Our software methods were validated on synthetic data but possibly on real datasets. LAMBDA strengthened existing links within Europe and across the Atlantic, while creating new synergies that support knowledge transfer beyond its lifetime.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

LAMBDA aims at transferring game changing technologies to the European industry in critical areas of Machine learning. Based on recent algorithmic breakthroughs, we adapt sophisticated methods to targeted industries, with a twofold goal: First, to help turn cutting edge tools into innovative software products and processes, tailored to real-world issues. Second, based on the available data, to organise open data repositories / benchmarks, or to simulate data with the same statistical properties, when such data is confidential, following ""anonymisation"".LAMBDA focuses on two distinct application domains: 3D shape analysis and unstructured data mining. They share challenging features such as inherent complexity in modeling the data, high dimensionality which raises the issue of curse of dimensionality, and the need to address such datasets at a massive scale. Moreover, they correspond to the expertise of the participants. LAMBDA is characterised by a unique blend of theoretically rigorous and geometrically inclined methods, thus supporting a strong aspect of interdisciplinarity between Theory of Algorithms and Machine Learning. This shall be supported by advanced software development, ranging from public-domain prototype implementations to licensed software and integrated libraries, where the latter may be based on the highly-optimised platform BIDMach (UC Berkeley).LAMBDA strengthens existing links within Europe and across the Atlantic, while creating new synergies in the directions of two industrial domains, namely 3D shape search and insurance data. The two clusters are organised around representative companies in the respective domains. The Project is built so as to support knowledge transfer beyond its lifetime. Besides inter-sectoral collaborations, we exploit the international dimension by associating leading USA Universities, so as to bring state-of-the-art methods developed at the global level into the European framework.""

Оригинален текст от CORDIS (на английски).

Участници

Връзки

Данни: CORDIS, © Европейски съюз