Issue #21
October 20, 2019
- 1. Causal Bayesian Networks: A flexible tool to enable fairer machine learning [deepmind.com]
- 2. Censorship of Harmful Data in Blockchains [blog.coinfabrik.com]
- 3. Big Question About Primes Proved in Small Number Systems [quantamagazine.org]
- 4. The current state of AI and Deep Learning: A reply to Yoshua Bengio [medium.com]
- 5. Top 5 mistakes with statistics in A/B testing [towardsdatascience.com]
- 6. Understanding the Backpropagation Algorithm [dev.to]
- 7. Beyond Word Embedding: Key Ideas in Document Embedding [kdnuggets.com]
- 8. TensorFlow 2.0 + Keras Overview for Deep Learning Researchers [colab.research.google.com]
- • Sampling can be faster than optimization (Y.-A. Ma, Y. Chen, C. Jin, N. Flammarion, M. I. Jordan)
- • Detecting different topologies immanent in scale-free networks with the same degree distribution (D. Tsiotas)
- • Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs (A. Jolicoeur-Martineau, I. Mitliagkas)
- • Success in books: predicting book sales before publication (X. Wang, B. Yucesoy, O. Varol, T. Eliassi-Rad, A.-L. Barabási)
- • Tutorial on NLP-Inspired Network Embedding (B. Shmueli)
- • Identifying Network Ties from Panel Data: Theory and an Application to Tax Competition (A. de Paula, I. Rasul, P. Souza)
Xavier Bresson: "Convolutional Neural Networks on Graphs"
All our videos are also available in our YouTube playlist.
Enjoy the newsletter?
Forward it to a friend, or subscribe to get it straight to your inbox.
Subscribe Free