Issue #109
June 27, 2021
This weeks Data Science Book is " The Hundred-Page Machine Learning Book " by Andriy Burkov. In this short book (despite the title, it in at 160 pages, but we won’t hold it against it) Burkov provides a high level overview of a broad range of Machine Learning topics that will appeal to beginners and perspective students who wish to get a quick survey of the breadth of possibilities afforded by ML algorithms before diving more deeply into the subject. While the book won’t convert you into a ML expert overnight, it does provide enough information and references to get you started and armed with enough baggage to be able to choose your own path. Another audience that will find the book useful is that of managers and those collaborating with data scientists and who need a solid understanding on the basics of this class of algorithms.
- 1. Machine Learning Model Interpretation [towardsdatascience.com]
- 2. Same or Different? The Question Flummoxes Neural Networks [quantamagazine.org]
- 3. Deep Learning for AI [cacm.acm.org]
- 4. Applied NLP Thinking: How to Translate Problems into Solutions [explosion.ai]
- 5. Concept Drift 101 [opendatascience.com]
- 6. Deep scatterplots [creatingdata.us]
- 7. A from-scratch tour of Bitcoin in Python [karpathy.github.io]
- • High-frequency trading and networked markets (F. Musciotto, J. Piilo, R. N. Mantegna)
- • Learning on knowledge graph dynamics provides an early warning of impactful research (J. W. Weis, J. M. Jacobson)
- • AI for radiographic COVID-19 detection selects shortcuts over signal (A. J. DeGrave, J. D. Janizek, S.-I. Lee)
- • Association between COVID-19 outcomes and mask mandates, adherence, and attitudes (D. Adjodah, K. Dinakar, M. Chinazzi, S. P. Fraiberger, A. Pentland, S. Bates, K. Staller, A. Vespignani, D. L. Bhatt)
- • Observation, experimentation, and replication in linguistics (J. Grieve)
- • Visualizing Evolving Trees (K. Gray, M. Li, R. Ahmed, S. Kobourov)
- • Graph Neural Networks for Natural Language Processing: A Survey (L. Wu, Y. Chen, K. Shen, X. Guo, H. Gao, S. Li, J. Pei, B. Long)
- • Machine Learning-Based Algorithms to Knowledge Extraction from Time Series Data: A Review (G. Ciaburro, G. Iannace)
- • Finding simplicity: unsupervised discovery of features, patterns, and order parameters via shift-invariant variational autoencoders (M. Ziatdinov, C. Y. Wong, S. V. Kalinin)
Applying Reinforcement Learning in Industry
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