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 Blacker the Box
“The faster the feedback on prediction accuracy, the blacker the box can be. The slower the feedback, the more your models should be explicit and formal.” - Data’s day of reckoning
“We can build a future we want to live in, or we can build a nightmare. The choice is up to us.” - The Mythos of Model Interpretability
In machine learning, the concept of interpretability is both important and slippery. - Ding! Always-on Alibaba office app fuels backlash among Chinese workers
“DingTalk sprang from Alibaba’s unsuccessful attempt to challenge the WeChat instant messenger of its arch-rival, Tencent Holdings Ltd, the service’s chief executive, Wu Zhao, said in an interview.” - ‘The discourse is unhinged’: how the media gets AI alarmingly wrong
“Social media has allowed self-proclaimed ‘AI influencers’ who do nothing more than paraphrase Elon Musk to cash in on this hype with low-quality pieces. The result is dangerous” - Google AI Chief Jeff Dean’s ML System Architecture Blueprint
“At this month’s Tsinghua-Google AI Symposium in Beijing, Dean discussed trends regarding the kinds of models scientists want to train. Google Brain research scientist Azalia Mirhoseini meanwhile gave a presentation on autoML with Reinforcement Learning at the same event.” … - Google’s AutoML: Cutting Through the Hype
… or not? “Given the above limitations, why has Google AutoML’s hype been so disproportionate to its proven usefulness (at least so far)? I think there are a few explanations.” - Machine Learning in Google BigQuery
“Today we’re announcing BigQuery ML, a capability inside BigQuery that allows data scientists and analysts to build and deploy machine learning models on massive structured or semi-structured datasets.” - Machine Learning Guides
From Google: Simple step-by-step walkthroughs to solve common machine learning problems using best practices. - Using Uncertainty to Interpret your Model
There are different types of uncertainty and modeling, and each is useful for different purposes. - Ten Techniques Learned From fast.ai
“Right now, Jeremy Howard – the co-founder of fast.ai – currently holds the 105th highest score for the plant seedling classification contest on Kaggle, but he’s dropping fast. Why? His own students are beating him. And their names can now be found across the tops of leaderboards all over Kaggle.” - PipelineAI: Optimize and Productionize Your Real-Time Machine Learning
Does contain continuous validation, looks interesting. - Monte Carlo simulation of airline overbooking
“We wrote a code in the Julia programming language to simulate the process of customers showing up to flights and identify the optimal amount to overbook.” - Keras implementation of Image OutPainting
This is an implementation of Painting Outside the Box: Image Outpainting paper from Standford University in Keras. - Points（PTS）
“Secure, fast & scalable blockchain-based data collaboration protocol. Bringing alive privacy-preserving & inclusive financial services for institutions, companies and consumers.” On the startup radar. Uses AI and Blockchain…
