Kedro – engineering best-practices library for data and ML pipelines. Comes with project cookiecutter, data access layer, built-in project oversight, Sphinx– and AirFlow integration, etc
— ML Review (@ml_review) February 4, 2020
By @QuantumBlackhttps://t.co/95bgwZMTOn pic.twitter.com/WN0Qjh5Zo4
New models from:
— Julien Chaumond (@julien_c) February 3, 2020
- @Wietsedv (Dutch BERT),
- @douwekiela at Facebook AI (MMBT, multi-modal model)
- @formiel, @laurent_besacie et al. (FlauBERT, French-trained XLM-like)
- @loretoparisi, @simofrancia et al. at @musixmatch (UmBERTo, Italian CamemBERT-like) pic.twitter.com/qgJ0fwqiwC
Given that data loading can be a major bottleneck in many DL projects, this sounds like an interesting project to check out: "Accelerating Pytorch with Nvidia DALI" --> "on small models it's ~4X faster than the Pytorch dataloader" https://t.co/W11D2OPCFf
— Sebastian Raschka (@rasbt) February 3, 2020
The cool kids may be moving to TabNet and NODE, mind you, although I don't have real-world experience of these yet.https://t.co/fiGASmkELY
— Jeremy Howard (@jeremyphoward) February 2, 2020
psyched both bc HuggingFace Transformer is going beyond text and bc this is happening with @douwekiela's multimodal bitransformer https://t.co/6qKhOoHRmX
— Kyunghyun Cho (@kchonyc) January 31, 2020
We are releasing HiPlot, a lightweight interactive visualization tool to help AI researchers discover correlations and patterns in high-dimensional data. https://t.co/4A2RpmOC1f pic.twitter.com/JckCuRpGsD
— Facebook AI (@facebookai) January 31, 2020
Excited to have my generative art project featured on @flowingdata today!
— Mike Freeman (@mf_viz) January 30, 2020
(Heavily based on a tutorial by @shiffman // @thecodingtrain)https://t.co/hsNJpTtdql
40x faster predictions for even the deepest random forests with @rapidsai FIL’s new sparse forest support - https://t.co/dLSJJ4W6C6
— RAPIDS AI (@rapidsai) January 30, 2020
Associated Press has posted its #rstats ggplot2 theme on GitHub (custom font may not be available) Larry Fenn tells #rstudioconf https://t.co/ZQoVSn3ume
— Sharon Machlis (@sharon000) January 30, 2020
Excited to release a library for explaining ML models using counterfactual examples. The idea is simple--explain a prediction by the minimal changes that would lead to a different outcome--but turns out generating a diverse set is challenging. https://t.co/B1167X30IU 1/3 https://t.co/WUBhrwVNtU
— Amit Sharma (@amt_shrma) January 29, 2020
PolyGame: An open-source framework for training AI players through self-play. Deals with many games, board size variation, partial observability...
— Yann LeCun (@ylecun) January 29, 2020
Interesting generalization tidbit: It plays Go on 19x19 at very good level after training only on 13x13.https://t.co/HslFgqyI37
Fun fact: Thinc actually implements all of the practical ideas from my "Let Them Write Code" keynote!
— Ines Montani 〰️ (@_inesmontani) January 28, 2020
1. Callbacks
2. Function registries
3. Entry points
4. Single-dispatch
🔮 Docs: https://t.co/8wfmqQQMhH
🖼 Slides: https://t.co/yrYbChgrH4
📺 Video: https://t.co/ddQOBQB7o9 https://t.co/3d6zNBBzXo
