Issue #105

May 30, 2021

This weeks Data Science Book is " Machine Learning for Time Series Forecasting with Python " by Francesca Lazzeri. This book take a modern approach to introducing time series forecasting using practical intuitive explanations of the fundamental concepts together with Python code that covers data preparation, deep learning and end-to-end model deployment in the cloud in a hands on manner and without getting bogged down with too many mathematical details.

Machine Learning for Time Series Forecasting with Python

1. How To Count A Billion Distinct Objects Using Only 1.5KB Of Memory [highscalability.com]
2. Hacker's guide to deep-learning side-channel attacks: the theory [elie.net]
3. Here are the data brokers quietly buying and selling your personal information [fastcompany.com]
4. Potemkin Data Science [mcorrell.medium.com]
5. Datasets for Google Cloud: Introducing our new reference architecture [cloud.google.com]
6. Be Careful When Interpreting Predictive Models in Search of Causal Insights [towardsdatascience.com]
7. Advancing sports analytics through AI research [deepmind.com]
8. How to Build a Machine Learning App [towardsdatascience.com]

• Impacts of social distancing policies on mobility and COVID-19 case growth in the US (G. A. Wellenius, S. Vispute, V. Espinosa, A. Fabrikant, T. C. Tsai, J. Hennessy, A. Dai, B. Williams, K. Gadepalli, A. Boulanger, A. Pearce, C. Kamath, et al)
• The universal visitation law of human mobility (M. Schläpfer, L. Dong, K. O’Keeffe, P. Santi, M. Szell, H. Salat, S. Anklesaria, M. Vazifeh, C. Ratti, G. B. West)
• Motifs for processes on networks (A. C. Schwarze, M. A. Porter)
• Are Pre-trained Convolutions Better than Pre-trained Transformers? (Y. Tay, M. Dehghani, J. Gupta, D. Bahri, V. Aribandi, Z. Qin, D. Metzler)
• Efficient hypothesis testing for community detection in heterogeneous networks by graph dissimilarity (X.-J. Xu, C. Chen, J. F. F. Mendes)
• Balancing the Spread of Two Opinions in Sparse Social Networks (D. Knop, Š. Schierreich, O. Suchý)
• Generalised learning of time-series: Ornstein-Uhlenbeck processes (M. Süzen, A. Yegenoglu)

Complex network analysis with NetworkX

May 30, 2021

​