Areas of interest include, but are not limited to: Active learning, Semi-supervised learning, Learning from "weak" labels/supervision, One/Zero-shot learning, Transfer learning/domain adaptation, Generative (Adversarial) Models, as well as methods that exploit structural or domain knowledge.
NGI Explorers Program is looking for Europe's Top researchers and innovators in emerging Internet technologies to join a unique opportunity in the US.
3-6 MONTH EXPEDITION TO THE US
Work directly with a US partner to accelerate your idea.
100% SPONSORSHIP PLAN
Financial support will be 100% sponsored with EU public grants.
A coach will give direct support throughout the expedition.
This topic focuses on the investigation and development of data-efficient machine learning methods that are able to leverage knowledge from external/existing data sources, exploit the structure of unsupervised data, and combine the tasks of efficiently obtaining labels and training a supervised model. Areas of interest include, but are not limited to: Active learning, Semi-supervised learning, Learning from "weak" labels/supervision, One/Zero-shot learning, Transfer learning/domain adaptation, Generative (Adversarial) Models, as well as methods that exploit structural or domain knowledge.
Furthermore, while fundamental machine learning work is of interest, so are principled data-efficient applications in, but not limited to: Computer vision (image/video categorization, object detection, visual question answering, etc.), Social and computational networks and time-series analysis, and Recommender systems.
Many recent efforts in machine learning have focused on learning from massive amounts of data resulting in large advancements in machine learning capabilities and applications.
However, many domains lack access to the large, high-quality, supervised data that is required and therefore are unable to fully take advantage of these data-intense learning techniques. This necessitates new data-efficient learning techniques that can learn in complex domains without the need for large quantities of supervised data.
A basic understanding of Machine Learning
Source: NGI Explorers Program
Illustration Photo: VFRAME is a computer vision toolkit designed for human rights researchers and investigative journalists. It provides customized state-of-the-art tools for object detection and quantification, scene classification, visual search, image annotation for creating datasets, APIs to integrate with existing workflows, the ability to train new algorithms, and graphic content filtering algorithms to reduce exposure to traumatic Content. (credits: Adam Harvey / Ars Electronica / Flickr Creative Commons Attribution-NonCommercial-NoDerivs 2.0 Generic (CC BY-NC-ND 2.0))