I am BEGGING ml folks to learn about the context of tasks. Every single one of these is built on explicitly anti-Black foundations.
— Rachael Tatman (@rctatman) January 7, 2022
Some quick primers:
- IQ: https://t.co/bgK7VYyfr5
- BMI: https://t.co/pq4uiEGsNM
- Predictive policing: https://t.co/Npp6T7JzV5 (esp page 38 on) https://t.co/Blz5EzgyFF
Everyone knows what the linear time series looks like. We’ve seen it every day for 2+ years. The spiral turns to cycles. https://t.co/FnmKPe2X8T
— Nathan Yau (@flowingdata) January 6, 2022
Active learning usually focuses on labeling examples with high prediction uncertainty to improve performance. Plot twist: removing the most difficult examples (based on confidence & variability) helped reaching good performance with *fewer* examples https://t.co/4XPqh9DsOf 1/4 pic.twitter.com/Grm9QmP2mz
— Sebastian Raschka (@rasbt) January 6, 2022
ray-skorch - distributed PyTorch on Ray with sklearn API https://t.co/vwx9d6FZPw
— /MachineLearning (@slashML) January 5, 2022
Wow, just realized that Watermark (IPython/Jupyter magic) turned 8 years old! Also just released a new version (https://t.co/mcWXveqldQ), and thx to contribs, you can now print your Conda env. Hah, managing notebooks for research, teaching, & book, I wish we added this earlier 😅 pic.twitter.com/c3XnNJtpfi
— Sebastian Raschka (@rasbt) January 4, 2022
Persformer: A Transformer Architecture for Topological Machine Learning
— AK (@ak92501) January 3, 2022
abs: https://t.co/Lkq5cl7a7D pic.twitter.com/HhyiC3s1Kz
After my post on real-time machine learning last year, many people asked me how to do it.
— Chip Huyen (@chipro) January 3, 2022
This post discusses the challenges + solutions for online prediction, online evaluation, and continual learning, with use cases and examples.
Feedback appreciated!https://t.co/lywDVpYnUD
Impressive results via data distillation (aka reducing a large dataset to a synthetic, smaller one). Here, the researchers represent the 50k images in CIFAR-10 via just 10 images. A model trained on these 10 img achieves 64% accuracy on the orig test set https://t.co/MZHHSaDcK5 pic.twitter.com/3LRn4xAOse
— Sebastian Raschka (@rasbt) December 29, 2021
Vision Transformer for Small-Size Datasets
— AK (@ak92501) December 28, 2021
abs: https://t.co/uy4e4Mo44m
SPT and LSA were applied to the ViTs, the performance improved by an average of 2.96% in TinyImageNet, which is a representative small-size dataset pic.twitter.com/QxZUoqJGCQ
A beautiful music transformer visualization of the final attention heads from @ashVaswani 's talk on "attention is all you need" at RAAIS 2019 https://t.co/XwSIKr4nm3
— Eric Jang 🇺🇸🇹🇼 (@ericjang11) December 26, 2021
The model learns to attend to periodic tokens when doing things like tremelos pic.twitter.com/znWCv5WWsU
an alternative way to imagine PCA: pic.twitter.com/VXXGBEDXic
— Karl Rohe (@karlrohe) December 20, 2021
I've been working on academic deep learning summarization a bunch. Now we are finally shipping a lot of useful summarization features at https://t.co/2tfrBwhwOc, eg. recipes https://t.co/colxgxPHlv
— Richard Socher (@RichardSocher) December 18, 2021
and
shopping reviews:https://t.co/1OF246JwBI pic.twitter.com/vIU2OVmVAD
