Тренировки ML

In this challenge, you will build a model to classify cloud organization patterns from satellite images. If successful, you’ll help scientists to better understand how clouds will shape our future climate. This research will guide the development of next-generation models which could reduce uncertainties in climate projections.

Using the cloud images of the past 96 hours taken by the weather satellite Himawari-8 and the corresponding weather analysis data to predict future cloud changes and create an algorithm that generates cloud images for the next 24 hours.

Every day, work-related injury records are generated. In order to alleviate the human effort expended with coding such records, the Centers for Disease Control and Prevention (CDC) National Institute for Occupational Safety and Health (NIOSH), in close partnership with the Laboratory for Innovation Science at Harvard (LISH), is interested in improving their NLP/ML model to automatically read injury records and classify them according to the Occupational Injury and Illness Classification System (OIICS).

Natural disasters caused USD 180 billion in damage in 2018 alone. Helping to alleviate these costs using data science, will be the focus of this year’s datathon. You will be asked to solve a social challenge, related to natural disasters, by applying state-of-the-art data science and combining them with consulting skills. You will solve the challenge end-to-end by creating the code, translating the output thinking about how to best applying what you have learnt to make a real difference and potentially save lives. Our experienced analytics consultants in each location will provide you with the opportunity to discuss your ideas and to problem solve.

Каждый поучаствует в двух задачах: производственной и маркетинговой. В каждой будет еще одна небольшая "подзадачка" в виде дополнительного трека. В основной маркетинговой задаче вам предстоит предсказать будущие котировки натурального каучука - естественного конкурента синтетического каучука, который производит компания СИБУР. В основной производственной необходимо научиться предсказывать будущую активность катализатора, который используется в процессе полимеризации.

Logistics in Sub-Saharan Africa increases the cost of manufactured goods by up to 320%; while in Europe, it only accounts for up to 90% of the manufacturing cost. Economies are better when logistics is efficient and affordable. Sendy, in partnership with insight2impact facility, is hosting a Zindi challenge to predict the estimated time of delivery of orders, from the point of driver pickup to the point of arrival at final destination.

In this competition, your challenge is to build an algorithm to detect acute intracranial hemorrhage and its subtypes.

As an “armchair quarterback” watching the game, you may think you can predict the result of a play when a ball carrier takes the handoff - but what does the data say? In this competition, you will develop a model to predict how many yards a team will gain on given rushing plays as they happen. You'll be provided game, play, and player-level data, including the position and speed of players as provided in the NFL’s Next Gen Stats data. And the best part - you can see how your model performs from your living room, as the leaderboard will be updated week after week on the current season’s game data as it plays out.

The Tellus Satellite Challenge is a data analysis contest aimed at promoting the use of Tellus, such as visualization of examples of utilization of satellite data, discovery of excellent analytical human resources, and dissemination and enlightenment of satellite data types and formats. Will be held. The third theme is “Detection of sea ice area using SAR data”.

Single-cell -omics Trajectory Inference (TI) methods are essential tools for the analysis of cellular dynamic process and to understand gene regulation. More than 60 methods have been developed and the list still keeps growing. It's time to bring fresh ideas to this emerging and exciting field and keep improving.

Соревнование алгоритмов классификации лесных пожаров по данным о температурных аномалиях со спутников. Необходимо по информации о точке температурной аномалии, классифицировать тип пожара (по классификации МЧС). Решение должно быть реализовано в виде программы, которая принимает на вход CSV таблицу с точками (координаты latitude, longitude и дата получения точки date). На выход необходимо формировать таблицу с вероятностями по каждому из 11 классов (колонки fire_1_prob, fire_11_prob).

In this competition, you’ll develop accurate predictions of metered building energy usage in the following areas: chilled water, electric, natural gas, hot water, and steam meters. The data comes from over 1,000 buildings over a three-year timeframe.

In this challenge, you will be predicting roof type from drone imagery. The data consists of a set of overhead imagery of seven locations across three countries with labeled building footprints. Your goal is to classify each of the building footprints with the roof material type.

Your challenge: develop an algorithm to estimate the absolute pose of vehicles (6 degrees of freedom) from a single image in a real-world traffic environment.

PBS KIDS, a trusted name in early childhood education for decades, aims to gain insights into how media can help children learn important skills for success in school and life. In this challenge, you’ll use anonymous gameplay data, including knowledge of videos watched and games played, from the PBS KIDS Measure Up! app, a game-based learning tool developed as a part of the CPB-PBS Ready To Learn Initiative with funding from the U.S. Department of Education. Competitors will be challenged to predict scores on in-game assessments and create an algorithm that will lead to better-designed games and improved learning outcomes. Your solutions will aid in discovering important relationships between engagement with high-quality educational media and learning processes.

In this competition, your goal is to predict short and long answer responses to real questions about Wikipedia articles. The dataset is provided by Google's Natural Questions, but contains its own unique private test set. A visualization of examples shows long and—where available—short answers. In addition to prizes for the top teams, there is a special set of awards for using TensorFlow 2.0 APIs.

The objective of this challenge is to build a machine learning model that accurately predicts when and where the next road incident will occur in Cape Town, South Africa. Data scientists will build their models on historic road incident data as well as traffic pattern data from Uber.

The objective of this challenge is the creation, curation and collation of good quality African language datasets for a specific NLP task. This task-specific NLP dataset will serve as the downstream task we can evaluate future language models on.