NumPy Illustrated: The Visual Guide to NumPy, by @LevMaximov
— hardmaru (@hardmaru) December 23, 2020
A nice visual guide to basic NumPy operations, vectorized computation, broadcasting, tiling/repeating/sorting ops.https://t.co/qYTzcsDw8I
NumPy Illustrated: The Visual Guide to NumPy, by @LevMaximov
— hardmaru (@hardmaru) December 23, 2020
A nice visual guide to basic NumPy operations, vectorized computation, broadcasting, tiling/repeating/sorting ops.https://t.co/qYTzcsDw8I
There are also several new tools for time series, i.e., the scikit-learn compatible sktime (https://t.co/XdV1RdQanq), its sktime-dl extension for DL and TensorFlow (https://t.co/UcRRxy2w0D), and pytorch-forecasting https://t.co/dtwVyx09Zu
— Sebastian Raschka (@rasbt) December 22, 2020
"Top 10 Python libraries of 2020": Really love @tryolabs yearly reviews & lists. https://t.co/ChGTTYO087
— Sebastian Raschka (@rasbt) December 22, 2020
HiPlot sounds like something I want to check out. A tool for discovering correlations and patterns in high-dimensional data using parallel plots pic.twitter.com/27lgEeUShh
In July, we shared a state of the art voice model that separates up to five different voices simultaneously speaking, improve the ability to reduce background noise, and enhance communication across a variety of applications. Code now on @PyTorch: https://t.co/4Trw7a8i5T pic.twitter.com/3CFeGNHIpB
— Facebook AI (@facebookai) December 22, 2020
Currently toying around with *gradient checkpointing* to fit some of my larger DL models into VRAM. Such a simple an neat trick for more memory-efficient backpropagation. Great article here: https://t.co/yeHWZiSYYw. There's also a PyTorch implementation: https://t.co/uXz7C5vCdM pic.twitter.com/KM7wIOeEvb
— Sebastian Raschka (@rasbt) December 22, 2020
data augmentation is really all you need, huh? https://t.co/amc2GP81XG pic.twitter.com/MLH6Ulp3JE
— Kyunghyun Cho (@kchonyc) December 22, 2020
Hypersim: Photorealistic Synthetic Dataset for Indoor Scene Understanding
— hardmaru (@hardmaru) December 22, 2020
Photorealistic synthetic scenes have the advantage of giving us as many ground truth layers as we want to train an ML system. But is it enough for sim2real?https://t.co/U4qXXKn6qFhttps://t.co/rTnWT4XvEE pic.twitter.com/aRa5K6unWh
Are slow Git clones bogging you down? Get up to speed with partial clone and shallow clone. https://t.co/FqzmfCk2Nr
— GitHub (@github) December 21, 2020
“Deaths per week: 2020 vs. previous 5 years” insightful way of visualizing COVID19 deaths. Also a way to show how well New Zealand has managed! Source: https://t.co/ODKRfV2f6k pic.twitter.com/JMo3cpKYsU
— Simon Kuestenmacher (@simongerman600) December 20, 2020
TabNet: Attentive Interpretable Tabular Learning
— ML Review (@ml_review) December 20, 2020
By @sercanarik @tomaspfister
Automates feature engineering for tabular models
Learns representations through unsupervised pre-training to predict masked features + supervised fine-tuning https://t.co/4xDY5O24tC pic.twitter.com/clKlkWH4sp
ML community: * create algorithms that optimize for a single objective *
— Chip Huyen (@chipro) December 20, 2020
Companies: * use ML to optimize for user engagement, which learns to favor extreme content since it gets the most attention *
ML community: “Why are people on Twitter getting so extreme?”
Excited to launch "ghapi" today in partnership with @GitHub. ghapi provides complete access to the entire GitHub API, using a consistent interface with many nice touches.
— Jeremy Howard (@jeremyphoward) December 18, 2020
See thread below for a demo and summary, or read the post for details: 1/https://t.co/DDzM6sm6Dw