Was trying to implement k-fold cross-validation for deep neural nets ...
— Sebastian Raschka (@rasbt) May 4, 2022
Phew, I was almost about to reinvent the wheel before I discovered the pl_cross library! Just put together a quick demo here: https://t.co/YQXPvFto2b
You might not believe it, but the following 6 machine learning books are fully free:
— Jean de Nyandwi (@Jeande_d) May 2, 2022
- Deep Learning
- Dive into Deep Learning
- Machine Learning Engineering
- Python Data Science Handbook
- Probabilistic Machine Learning
- Machine Learning Yearning
Here are their links 🧵 pic.twitter.com/TMEu5hB2MX
The Annotated Transformer [v2022]
— Sasha Rush (@srush_nlp) May 2, 2022
A community refresh of the original blog with modern PyTorch and data-science tools. https://t.co/6jydMTO8if
(Led by @austinvhuang, @subramen, @JonathanSumDL, @eKhalid_, @BlancheMinerva ) pic.twitter.com/mMhcdw5Mbu
This past weekend there was a major announcement by the @anacondainc team at #PyCon2022 - the launch of PyScript, an in-HTML interface for Python. This is something that many of us in the Python community have been hoping for for a long time. #Python #Web #Programming
— Bojan Tunguz (@tunguz) May 2, 2022
1/6 pic.twitter.com/e81H58VSZg
Excited to see https://t.co/OhatkRLd0H from @anacondainc
— Soumith Chintala (@soumithchintala) April 30, 2022
A well-supported effort to put Python in the browser has so much benefit.
Immediately, the powerful Dashboards and ipython widgets which we write in Javascript today can and should be moved to Pyscript
pyscript wrapper for D3
— Hamel Husain (@HamelHusain) April 30, 2022
WOW, Data Scientists can write D3 with Python now
This is the coolest thing that's happened to DataViz in a while https://t.co/X6DF0Uk7E2
Marathon records by age and gender. Sharing this for the crazy 80 year old running a sub four hour Marathon. Source: https://t.co/GtalGxwnW2 pic.twitter.com/Q8Jakm5C7h
— Simon Kuestenmacher (@simongerman600) April 29, 2022
Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework
— AK (@ak92501) April 29, 2022
abs: https://t.co/N4PZEKFIey
github: https://t.co/CsRcp667Ge pic.twitter.com/z4IfiuTfpj
If you are working in Python, and find yourself in a need of encoding categorical variables for various ML tasks, I'd strongly encourage you to take a look at the Category Encoders library. It's a very good and fairly comprehensive sklearn-style library. https://t.co/N8wubPlKDF
— Bojan Tunguz (@tunguz) April 28, 2022
Interesting work on making the stride parameter of convolutional layers learnable. No, it doesn't require discrete optimization as in conventional NAS but is based on gradient descent. Code curently only for TF, but should be portable to PyTorch. https://t.co/QtRrY4KpSZ pic.twitter.com/5wFOtTPpn9
— Sebastian Raschka (@rasbt) April 27, 2022
Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items
— AK (@ak92501) April 27, 2022
abs: https://t.co/eVRIkbLeqp pic.twitter.com/jRDQEYfYnV
Understanding The Robustness in Vision Transformers
— AK (@ak92501) April 27, 2022
abs: https://t.co/reQ35twd49
model achieves a state-of-the-art 87.1% accuracy and 35.8% mCE on ImageNet-1k and ImageNet-C with 76.8M parameters pic.twitter.com/H5pTsUpEE0
