Using weather data in machine learning is promising. For instance, everyone knows that weather forecast influences buying patterns, be it for apparel, food, or travel. Wouldn't it be nice to capture weather forecast effect on these? All we need to do is to use weather data in addition to other data we have, then use our favorite machine learning toolbox. It sounds simple but there is a catch.

It's a struggle because deep learning is taught by academics, for academics. The way practitioners learn new technologies is by developing prototypes that deliver value quickly. This is a top-down approach to learning, but it is not the way that deep learning is taught. A way that works for top-down practitioners like you. You will believe that being successful with applied deep learning is possible.

You schedule a doctor's appointment and immediately your phone buzzes with a notification -- you're now eligible to save a few hundred bucks on your deductible. It may not be a reality quite yet, but experts at UPMC Enterprises say machine learning, advanced access to patient data, and artificial intelligence could soon make your medical care a lot more personal. "Imagine getting an alert that tells you you're close to getting a deduction," said Mohinder Dick, senior software architect at UPMC Enterprises. "I routinely get those kinds of updates from my cable company or Amazon. Why can't we get the same convenience from health care?"

Machine learning used to take place behind the scenes: Amazon mined your clicks and purchases for recommendations, Google mined your searches for ad placement, and Facebook mined your social network to choose which posts to show you. But now machine learning is on the front pages of newspapers, and the subject of heated debate. Learning algorithms drive cars, translate speech, and win at Jeopardy! What can and can't they do? Are they the beginning of the end of privacy, work, even the human race?

Today there were a number of interesting items I have found and recommend for viewing. One is a lot of content from H2O's recent event, some Python libraries, and a few presentations. H2O had a great conference in NYC recently all around their open source Machine Learning and Deep Learning platform that works with Hadoop and Spark. I have chosen some of the best slide presentations and videos below. H2O Sparkling Water is their ML/DL library on top of Apache Spark.

What does "causality" mean, and how can you represent it mathematically? How can you encode causal assumptions, and what bearing do they have on data analysis? These types of questions are at the core of the practice of data science, but deep knowledge about them is surprisingly uncommon. If you analyze data without regard to causality, you open your results up for the possibility of enormous biases. This includes everything from recommendation system results, to post-hoc reports on observational data, to experiments run without proper holdout groups. I've been blogging a lot recently about causality, and wanted to go through some of the material at a more technical level. Recent posts have been aimed at a more general audience. This one will be aimed at practitioners, and will assume a basic working knowledge of math and data analysis. To get the most from this post you should have a reasonable understanding of linear regression and probability (although we'll review a lot of probability). Prior knowledge of graphical models will make some concepts more familiar, but is not required. Judea Pearl, in his book Causality, constantly remarks that until very recently, causality was a concept in search of a language.

Lounge apparel retailer FlyPolar uses a new service from vendor Sentient Technologies to test many elements quickly across multiple pages and is on track to double sales this month. Artificial intelligence can lead to real sales increases--and fast ones, too. Just ask loungewear retailer ShopFlyPolar.com. The web only merchant had hit a sales downturn, generating about 277,000 in web sales in February 2015 to about 50,000 in July 2016 says, says Shawn Broadus founder and CEO of FlyPolar. "We hit a slump," Broadus say.

The first thing that might come to mind thinking of drones is their military application. Unmanned flying weaponry, however, is not a new approach. In the 1860s, balloons loaded with explosives and sent with the prevailing winds towards enemy targets, were used as the first drones. Today, they have become such an innovative technology that its use has extended to the civilian and commercial sector, becoming a part of our everyday life. Unmanned aircraft systems (UAS) or by the public referred as drones, have the potential to solve problems, improve safety and save costs across a number of industries, throughout the developing world and in disaster relief scenarios.

This story was delivered to BI Intelligence "E-Commerce Briefing" subscribers. To learn more and subscribe, please click here. The acquisition is part of the e-commerce company's structured data push for sellers. Structured data is eBay's standard way of categorizing and displaying products for sale on its marketplace. Utilizing SalesPredict's data analysis and machine learning skills, eBay will be able to better refine its search functions in order to serve the right products to prospective shoppers.

When police officers removed the mirrored doors behind which Yonatan Daniel Aguilar had died hours earlier, they found a crumpled blanket on the ground, obscuring his emaciated body -- pale and stiff, curled in a fetal position, with cuts on his face. One officer lifted a corner of the blanket and two cockroaches crawled out. The child was so tiny that officers thought maybe he was 6 years old or so. Details about the condition of Yonatan's body when it was found last month in his Echo Park home were disclosed in more than 100 pages of heavily-redacted case records and police reports released to The Times by the Los Angeles County Department of Children and Family Services this week. The records show that Yonatan's risk of abuse at home had been marked as "high" four times from 2009 to 2012 by a county program intended to guide social workers' level of intervention.