Название: Automated Machine Learning: Methods, Systems, Challenges Автор: Frank Hutter, Lars Kotthof, Joaquin Vanschoren
Издательство: Springer
Год: 2019
Страниц: 222
Язык: английский
Формат: pdf (true), epub
Размер: 19.8 MB
В этой книге представлен первый всеобъемлющий обзор общих методов автоматического машинного обучения (AutoML), собраны описания существующих систем на основе этих методов и обсуждена первая серия международных проблем систем AutoML. Недавний успех коммерческих приложений машинного обучения (ML) и быстрый рост области создали высокую потребность в готовых методах ML, которые могут использоваться легко и без экспертных знаний. Тем не менее, многие из последних успехов в машинном обучении в значительной степени зависят от человеческих экспертов, которые вручную выбирают подходящие архитектуры ML (архитектуры глубокого обучения или более традиционные рабочие процессы ML) и их гиперпараметры. Чтобы преодолеть эту проблему, область AutoML нацелена на прогрессивную автоматизацию машинного обучения, основанную на принципах оптимизации и самого машинного обучения. Эта книга служит отправной точкой в ??этой быстро развивающейся области как для исследователей, так и для продвинутых студентов, а также представляет собой справочник для практиков, стремящихся использовать AutoML в своей работе.
This open access book presents the first comprehensive overview of general methods in Automated Machine Learning (AutoML), collects descriptions of existing systems based on these methods, and discusses the first series of international challenges of AutoML systems. The recent success of commercial ML applications and the rapid growth of the field has created a high demand for off-the-shelf ML methods that can be used easily and without expert knowledge. However, many of the recent machine learning successes crucially rely on human experts, who manually select appropriate ML architectures (deep learning architectures or more traditional ML workflows) and their hyperparameters. To overcome this problem, the field of AutoML targets a progressive automation of machine learning, based on principles from optimization and machine learning itself. This book serves as a point of entry into this quickly-developing field for researchers and advanced students alike, as well as providing a reference for practitioners aiming to use AutoML in their work.
The field of automated machine learning (AutoML) aims to make these decisions in a data-driven, objective, and automated way: the user simply provides data, and the AutoML system automatically determines the approach that performs best for this particular application. Thereby, AutoML makes state-of-the-art machine learning approaches accessible to domain scientists who are interested in applying machine learning but do not have the resources to learn about the technologies behind it in detail. This can be seen as a democratization of machine learning: with AutoML, customized state-of-the-art machine learning is at everyone’s fingertips.
As we show in this book, AutoML approaches are already mature enough to rival and sometimes even outperform human machine learning experts. Put simply, AutoML can lead to improved performance while saving substantial amounts of time and money, as machine learning experts are both hard to find and expensive. As a result, commercial interest in AutoML has grown dramatically in recent years, and several major tech companies are now developing their own AutoML systems. We note, though, that the purpose of democratizing machine learning is served much better by open-source AutoML systems than by proprietary paid black-box services.
Скачать Automated Machine Learning: Methods, Systems, Challenges