Issue #99
April 18, 2021
This weeks Data Science Book is " Transformers for Natural Language Processing " by D. Rothman. Transformers are the latest generation deep learning architecture for NLP that gained prominence in recent years by surpassing the performance of RNNs, GRUs and LSTMs. This book provides a grounded introduction to Transformers from the perspective of cognitive science so that you can quickly master the fundamentals and grow to apply them to your own work.
- 1. Europe seeks to limit use of AI in society [bbc.com]
- 2. The True Meaning of Technical Debt [refactoring.fm]
- 3. Timeline of Mathematics [mathigon.org]
- 4. Bloom filters [exampl.io]
- 5. Unifying the CUDA Python Ecosystem [developer.nvidia.com]
- 6. Gigerenzer’s simple rules [foundingfuel.com]
- 7. Announcing the Neo4j GraphQL Library Beta Release [medium.com/neo4j]
- 8. Reinforcement Learning: What is, Algorithms, Applications, Example [guru99.com]
- • Fresh teams are associated with original and multidisciplinary research (A. Zeng, Y. Fan, Z. Di, Y. Wang, S. Havlin)
- • Causal Decision Making and Causal Effect Estimation Are Not the Same... and Why It Matters (C. Fernández-Loría, F. Provost)
- • Denialism: what is it and how should scientists respond? (P. Diethelm, M. McKee)
- • Cross-validation: what does it estimate and how well does it do it? (S. Bates, T. Hastie, R. Tibshirani)
- • Bayesian collective learning emerges from heuristic social learning (P. M. Krafft, E. Shmueli, T. L. Griffiths J. B. Tenenbaum, A. Pentland)
- • Shapley Explanation Networks (R. Wang, X. Wang, D. I. Inouye)
- • Deep Learning-based Online Alternative Product Recommendations at Scale (M. Guo, N. Yan, X. Cui, S. H. Wu, U. Ahsan, R. West, K. A. Jadda)
SHAP Values for ML Explainability
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