In a previous tutorial series I went over some of the theory behind Recurrent Neural Networks (RNNs) and the implementation of a simple RNN from scratch. That's a useful exercise, but in practice we use libraries like Tensorflow with high-level primitives for dealing with RNNs. With that using an RNN should be as easy as calling a function, right? In this post I want to go over some of the best practices for working with RNNs in Tensorflow, especially the functionality that isn't well documented on the official site. Check out the tf.SequenceExample Jupyter Notebook here! RNNs are used for sequential data that has inputs and/or outputs at multiple time steps.

The new Bedtime feature is a new kind of alarm – meant not only to be set for when you wake up, but also when you should be going to sleep. It aims to make sure that people spend enough time in bed by alerting them to their sleep time, and analysing whether or not they're actually making it into bed on time. It's used by heading to the Clock app in iOS 10, where there is a new tab at the bottom. There, you'll get the option to add what time you want to wake up and then what time you want to go to sleep. This might be the first thing you notice, and it's probably the most significant change to your daily routine.

September is fast approaching and so is London Design Festival and the Digital Design Weekend! Now in its sixth year, the Digital Design Weekend will bring together again over a hundred artists, designers, engineers, technologists and of course the public to celebrate and share contemporary digital art and design, take part in interactive installations and labs, engage in conversations, and learn about processes. Over the weekend we will be taking over the Museum to showcase a huge programme of cutting edge, international digital projects, but also performances, talks, open workshops, labs and family-friendly activities, all exploring engineering, making and collaboration. The Weekend will include many protoyping events and workshops, such as the Open IoT Design Sprint with Mozilla Open IoT Studio & collaborators* to make & share prototypes that serve local communities & celebrate the unique affordances of physical places; a Biosynth workshop to introduce basic electronics and biology interactions by Andreas Siagian from Indonesia's Lifepatch; a Storm Laboratory with Loop.ph to experience the turbulent nature of geophysical air dynamics, as well as a hydroponic system workshop, a co-design performance workshop and many more. There is lots for young people and families to enjoy, including, a Build Your Own Pavilion Young Architects Challenge by the Serpentine Galleries and Kidesign challenging budding young architects to design the pavilions of the future; Scan the World by MyMiniFactory, inviting families to help scan the V&A's collections and see 3D printers in action; a Tanglebot workshop with unruly robots, wool, Lego and Raspberry PIs, as well as many family-friendly installations and other activities.

In the data science course that I instruct, we cover most of the data science pipeline but focus especially on machine learning. Besides teaching model evaluation procedures and metrics, we obviously teach the algorithms themselves, primarily for supervised learning. Near the end of this 11-week course, we spend a few hours reviewing the material that has been covered throughout the course, with the hope that students will start to construct mental connections between all of the different things they have learned. One of the skills that I want students to be able to take away from this course is the ability to intelligently choose between supervised learning algorithms when working a machine learning problem. Although there is some value in the "brute force" approach (try everything and see what works best), there is a lot more value in being able to understand the trade-offs you're making when choosing one algorithm over another.

When Sebastian Thrun started working on self-driving cars at Google in 2007, few people outside of the company took him seriously. "I can tell you very senior CEOs of major American car companies would shake my hand and turn away because I wasn't worth talking to," said Thrun, now the co-founder and CEO of online higher education startup Udacity, in an interview with Recode earlier this week. A little less than a decade later, dozens of self-driving startups have cropped up while automakers around the world clamor, wallet in hand, to secure their place in the fast-moving world of fully automated transportation. And these companies are hungry for talent and skill sets many don't have. "Uber has just bought a half-a-year-old company [Otto] with 70 employees for almost 700 million," Thrun said.

We need the following manual steps to complete the data factory.

It has been 73 years since the Supreme Court ruled that students in public schools couldn't be forced to pledge allegiance to the American flag or engage in other patriotic demonstrations. But some educators obviously haven't gotten the message. In recent days, a principal in Florida told students they would be ejected from sports events if they didn't stand during the national anthem. A student in Northern California said her class-participation grade was lowered because she refused to stand during the Pledge of Allegiance, her chosen form of protest over the mistreatment of her Native American ancestors. A high school football player in Massachusetts said he was told he would be suspended if he emulated San Francisco 49ers quarterback Colin Kaepernick and knelt during the national anthem.

At our recent bots, ai & messaging meetup we talked through our thoughts on simplifying the bot strategy and design process -- from objectives to conversation trees and beyond. Here is a roundup of our latest thoughts on designing and building effective messaging applications, bots and more. The first step in the bot planning process is deciding what the bot will do for the bot's creator, and what it will do for the bot's users. There's no point in in making something no-one will want to use, and no point in making something that does nothing for your business. So define both sets of objectives clearly and look for how these could overlap within a messaging application.

The new Surface Complete for Education warranty program allows schools to pool their accidental damage claims. Microsoft R Server Developer Edition is now available on the Linux version of the company s Data Science Virtual Machine (DSVM), enabling users to build models using Microsoft s ScaleR libraries. In January, Microsoft launched R Server Developer Edition, a free version of the analytics platform for developers, students and nonproduction deployments. The offering arrived nearly a year after the software maker announced it was acquiring Revolution Analytics, the leading commercial supporter of R, the popular open-source statistical computing language. Making Microsoft R Server Developer available on the Linux flavor of the DSVM offers a major bump in big data processing capabilities.

Data School's 8-week Master Course begins September 28. More than two-thirds of the available spots are gone! Learn more about the course and enroll: http://www.dataschool.io/learn/ This info session was recorded on September 13. View the chat history and complete Q&A: http://ccst.io/e/text-course