And the deep learning vs conventional machine learning for tabular data continues!
— Sebastian Raschka (@rasbt) July 23, 2022
A new paper looks at 45 mid-sized datasets (10k examples) and finds that tree-based models (XGBoost & random forests) still outperform deep neural networks on tabular datasets. [1/6] pic.twitter.com/Xp1BDSHNtk
Contrary to what grad school wants you to believe, staying up late to work on your ML projects is actually bad (for the environment).
— Sebastian Raschka (@rasbt) July 22, 2022
Training a model at midnight increases CO2 emissions by 7.7% compared to 6:00 am. https://t.co/W1b3Vc9JxR pic.twitter.com/F2bWpX2tSe
Time and object detectors are running by so fast!
— Sebastian Raschka (@rasbt) July 20, 2022
Feels like I was using YOLOv3 just a few years ago. This month, YOLOv7 was released!
It's 1500% faster than a SWIN Transformer-based R-CNN (at the same accuracy) and 150% faster than YOLOv5!https://t.co/fdHnzNPj2n pic.twitter.com/byeT9ftAbT
here's where i'm at right now pic.twitter.com/vNwrcvd0jE
— tj mahr 🍍🍕 (@tjmahr) July 19, 2022
We investigate what features of tabular data explain the difference, for this, we modify tabular data to narrow the gap.
— Gael Varoquaux (@GaelVaroquaux) July 19, 2022
Smoothing the outcome in feature space narrows the gap: deep architectures struggle with irregular patterns. Tree models do not care about smoothness
6/9 pic.twitter.com/NlyvuzwlgD
“Create grammar-of-graphics calendars” with the {ggcalendar} #rstats 📦 by @EvaMaeRey version 0.0.0.9 on GitHubhttps://t.co/khIDo70Scr pic.twitter.com/BFkhZ9Lqbs
— Sharon Machlis (on staycation & offline for a bit) (@sharon000) July 16, 2022
I would like to share with you the actual narrative of an actual published paper :-\
— Casey Fiesler, PhD, JD, geekD (@cfiesler) July 16, 2022
- LGBT people have privacy concerns so they might be reluctant to participate in research
- So we built a machine learning classifier to identify them on Twitter so they can be researched anyway
Tired of spinning Jupyter notebooks on GitHub 😵💫, check out @yuvipanda’s faster way of sharing notebooks at https://t.co/eSvZe3Xvx9 👌👌👌 #SciPy2022
— Sebastian Raschka (@rasbt) July 14, 2022
Along with the @YouTube search team, we developed AutoChapters, an AI system that can rapidly summarise video transcripts and suggest chapter and video titles for YouTube creators. AutoChapters has helped save time for viewers and content creators alike. 4/4 pic.twitter.com/bne7mz2Oeo
— DeepMind (@DeepMind) July 14, 2022
The Technology Behind BLOOM Training🌸
— Hugging Face (@huggingface) July 14, 2022
Discover how @BigscienceW used @MSFTResearch DeepSpeed + @nvidia Megatron-LM technologies to train the World's Largest Open Multilingual Language Model (BLOOM):https://t.co/8QOxhrIVbs
N-Grammer: Augmenting Transformers with latent n-grams
— AK (@_akhaliq) July 14, 2022
abs: https://t.co/Rx9wzbjoHj
propose modification to the Transformer architecture by augmenting the model with n-grams that are constructed from a discrete latent representation of the text sequence pic.twitter.com/RzrRBcVGR9
One of my data friends emailed this to me. I’m in tears 🤣🤣🤣 pic.twitter.com/rSPmv5Lsci
— Simon Kuestenmacher (@simongerman600) July 12, 2022
