Posted on August 30, 2019 by Arber Zela, Yassine Marrakchi, Frank Hutter
By Compared to the state of computer vision 20 years ago, deep learning has enabled more generic methodologies that can be applied to various tasks by automatically extracting meaningful features from the data. However, in practice those methodologies are not as generic as it looks at first glance. While standard neural networks may lead to […]
Posted on August 18, 2019 by Thomas Elsken
By Most work on neural architecture search (NAS, see our recent survey) solely optimizes for one criterion: high performance (measured in terms of accuracy). This often results in large and complex network architectures that cannot be used in real-world applications with several other important criteria including memory requirement, energy consumption and latency. The other problem […]
Posted on August 9, 2019 by Frank Hutter
By Much work in neural architecture search (NAS) is extremely compute hungry — so compute hungry that it hurts progress and scientific rigor in the community. When individual experiments require 800 GPUs for weeks nobody in academia can meaningfully join the community, and even in companies with huge compute resources nobody thinks of repeating their […]
Posted on August 7, 2019 by Frederic Runge, Danny Stoll
By In reinforcement learning (RL), one of the major machine learning (ML) paradigms, an agent interacts with an environment. How well an RL agent can solve a problem, can be sensitive to choices such as the policy network architecture, the training hyperparameters, or the specific dynamics of the environment. A common strategy to deal with […]
Posted on July 26, 2018 by André Biedenkapp, Frank Hutter
By Machine learning has achieved many successes in a wide range of application areas, but more often than not, these strongly rely on choosing the correct values for many hyperparameters (see e.g. Snoek et al., 2012). For example, we all know of the awesome results deep learning can achieve, but when we set its learning […]
Posted on July 13, 2018 by André Biedenkapp, Katharina Eggensperger, Matthias Feurer, Frank Hutter
By Our ML Freiburg lab is the world champion in automatic machine learning (AutoML) again! After winning the first international AutoML challenge (2015-2016), we also just won the second international AutoML challenge (2017-2018). Our system PoSH-Auto-sklearn outperformed all other 41 participating AutoML systems.
