— Sponsored Link —
The AI Conference is where cutting-edge science meets new business implementation. It's a deep dive into emerging AI techniques and technologies with a focus on how to use it in real-world applications. Presented by O'Reilly Media and Intel. Save 20% on most passes when you use the discount code ELIXIR20.
— Tools and Techniques —
To understand why recommenders don’t always work as well as expected, the team at Fast Forward Labs built some basic recommendation systems and dissected them. Here's what they found.
Booking.com is massive and as it continues to refine its products, new changes produce smaller and smaller effects. Even so, with over 1.5 million transactions each day, even a fraction-of-a-percent change in conversion can make a big difference to profits. Here's a practical look at how Booking.com's data scientists use a technique called CUPED to optimize experiments and squeeze new profits out of its products.
Shirin Glander's latest post describes an easy way to create a web API for a trained machine learning model. Once you have the API, other programs can access your model and use it to make predictions. This post is easy to follow and includes information about handling security on a production server.
— Blogs —
This week's picks from around the community:
— Resources —
Kaggle introduced a new learning platform this week called Kaggle Learn. This is an awesome resource with tracks for Machine Learning, R, Data Visualization, and Deep Learning. Everything is free and each track includes a sequence of Notebooks with everything you need.
This new podcast from the folks at DataCamp is off to a great start. DataFramed is hosted by Hugo Bowne-Anderson and already has a great line-up of interviews. This will definitely be worth paying attention to.
Rollbar detects when code breaks in real-time. Get stack trace + diagnostic data to defeat errors.
— Deep Learning —
Here's a great tutorial that shows how to build a practical deep learning application and doesn't need a PhD to understand. Uses Keras and TensorFlow to summarize text and generate features from Github Issues.
A new generation of neural networks are inspired by biological models and rely on discrete, rather than continuous, values. Here's a high-level look at how these "spiking neural networks" work with insights into their practicality.
— Career —
Eric Mayefsky has assessed hundreds of job candidates at various tech companies. But like any manager, he started on the other side of the interview: as an applicant. In this post, Eric shares what he’s learned and offers useful insights to people on both sides of the table.