The third day of SciPy 2020 was filled with interesting and foundational tutorial content regarding deep learning with a short primer to the PyTorch library and I found the time to watch some interesting SciPy talks from Enthoughts SciPy Youtube channel as well.
Day two of the SciPy 2020 conference was also very informative. Except of some connectivity issues with my internet provider, which lead to missing the latter half of the awesome Dask tutorial and prevented me from listening to other talks, everything went equally smooth.
I am very happy 😄 to participate at the 2020 edition of the SciPy conference, which is held online thanks to the measures that prevent the spread of the COVID-19 virus. Although it is the first online version of the SciPy conference, everything works fine and fluently due to the tremendous help from the organizers and community.
Missing data, especially missing data points in time series, are a pervasive issue for many applications relying on precise and complete data sets. For example in the financial sector, missing tick data can lead to deviating forecasts and thus to wrong decisions with high losses.
As ubiquitous as time series are, it is often of interest to identify clusters of similar time series in order to gain better insight into the structure of the available data. However, unsupervised learning from time series data has its own stumbling blocks. For this reason, the following article presents some helpful time series specific distance metrics and basic procedures to work successfully with time series data.
Quite often it is the case that cyclic data is not sufficiently transformed for machine learning algorithms, e.g. feature representation is missing out on the implicit properties of cyclic features often resulting in wrong distance measures. This article introduces cyclic feature transformation for time based features as a mini-howto.
Many deep reinforcement learning methods have been established for the development of autonomous AI-agents. This talk introduces deep reinforcement learning as combination of deep learning and reinforcement learning and highlights a selection of noteworthy advancements since Mnih et al. introduced Deep Q-learning.