Issue #11

August 11, 2019

---

1. 1. Keras Learning Rate Finder [pyimagesearch.com]
2. 2. Can AI identify a Financial Bubble? [Data Driven Investor]
3. 3. Why Word Vectors Make Sense in Natural Language Processing [Open Data Science]
4. 4. Building our Centralized Experimental Platform [Multithreaded]
5. 5. Multi-Armed Bandits and Conjugate Models [eigenfoo.xyz]
6. 6. Decaying Evidence and Contextual Bandits [eigenfoo.xyz]

---

• • Bursty time series analysis for temporal networks (H.-H. Jo, T. Hiraoka)
• • Towards Federated Learning at Scale: System Design (K. Bonawitz, H. Eichner, W. Grieskamp, D. Huba, A. Ingerman, V. Ivanov, C. Kiddon, J. Konečný, S. Mazzocchi, H. B. McMahan, T. V. Overveldt, D. Petrou, D. Ramage, J. Roselander)
• • One Model To Rule Them All (F. Berkhahn, R. Keys, W. Ouertani, N. Shetty, D. Geißler)
• • Tweets Can Tell: Activity Recognition using Hybrid Long Short-Term Memory Model (R. Cui, G. Agrawal, R. Ramnath)
• • AutoML: A Survey of the State-of-the-Art (X. He, K. Zhao, X. Chu)
• • The Myths of Our Time: Fake News (V. Růžička, E. Kang, D. Gordon, A. Patel, J. Fashimpaur, M. Zaheer)
• • Deep Learning using Convolutional LSTM estimates Biological Age from Physical Activity (S. A. Rahman, D. A. Adjeroh)

---