Every two weeks, we find the most interesting data science links from around the web and collect them in Data Science Briefings, the DataMiningApps newsletter. Subscribe now for free if you want to be the first to get up to speed on interesting resources.
- The World’s Best Machine Learning Courses in 2019
Our friends over at CourseDuck have compiled more than 10,000 student reviews across 150+ of the web’s top Machine Learning courses, tutorials in search of the best way to learn Machine Learning in 2020.
- Our Neophobic, Conservative AI Overlords Want Everything to Stay the Same
Machine learning is fundamentally conservative, and it hates change.
- Why Are We Using Black Box Models in AI When We Don’t Need To? A Lesson From An Explainable AI Competition
“The belief that accuracy must be sacrificed for interpretability is inaccurate. It has allowed companies to market and sell proprietary or complicated black box models for high-stakes decisions when very simple interpretable models exist for the same tasks.”
- Training a single AI model can emit as much carbon as five cars in their lifetimes
Deep learning has a terrible carbon footprint.
- Beyond L2 Loss — How we experiment with loss functions at Lyft
Very informative article on Bregman and Patton losses!
- We Feared Deepfakes. Then Tech Monetized Them
TikTok and Snap are experimenting with deepfake-style filters
- Generative adversarial networks
What GANs are and how they’ve evolved
- Self-supervised learning and computer vision
“The secret is “self-supervised learning”. This is where we train a model using labels that are naturally part of the input data, rather than requiring separate external labels.”
- Facebook Discovers Fakes That Show Evolution of Disinformation
Researchers said the profiles, linked to the Epoch Media Group, used photos generated by artificial intelligence in a preview of an “eerie, tech-enabled future of disinformation.”
- Automatic Differentiation via Contour Integration
“Given the usefulness of partial derivatives for closed-loop control, it is natural to ask how might large branching structures in the brain and other biological systems compute derivatives.”
- Algorithm Removes Water from Underwater Images
“Why do all the pictures you take underwater look blandly blue-green? The answer has to do with how light travels through water. Derya Akkaynak, an oceangoing engineer, has figured out a way to recover the colorful brilliance of the deep.”
- Machine Learning Can’t Handle Long-Term Time-Series Data
More precisely, today’s machine learning (ML) systems cannot infer a fractal structure from time series data.
- The Twelve Truths of Machine Learning for the Real World
“6. It is easier to ignore or move a problem around than it is to solve it”
- The Central Limit Theorem and its misuse
“We warn about the mistake of approximating any distribution by a normal one. This is a very common misconception, that if we take enough samples the distribution of whatever it is we’re studying will be (close to) normal.”
- How Focus Became More Valuable Than Intelligence
“This may be the most important problem of our lifetime.”
- What’s next for the popular programming language R?
“Generally, there are a lot of people who talk about R versus Python like it’s a war that either R or Python is going to win. I think that is not helpful because it is not actually a battle. These things exist independently and are both awesome in different ways.”
- The Case for Bayesian Deep Learning
“Bayesian inference is especially compelling for deep neural networks. The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule.”
- A Sober Look at Bayesian Neural Networks
“We argue that BNNs require highly informative priors to handle uncertainty. We show that if the prior does not distinguish between functions that generalize and functions that don’t, Bayesian inference cannot provide useful uncertainties.”
- Using Machine Learning to “Nowcast” Precipitation in High Resolution
“We are presenting new research into the development of machine learning models for precipitation forecasting that addresses this challenge by making highly localized “physics-free” predictions that apply to the immediate future.”
- An algorithm that learns through rewards may show how our brain does too
By optimizing reinforcement-learning algorithms, DeepMind uncovered new details about how dopamine helps the brain learn.
- Machine Learning Interpretability: Why and How (presentation)
Nota is a nice terminal calculator with rich notation rendering.
Milvus is an open source similarity search engine for massive-scale feature vectors
HTTPX is a fully featured HTTP client for Python 3, which provides sync and async APIs, and support for both HTTP/1.1 and HTTP/2.
A visual analysis toolkit for accelerating text generation research