Sales forecast is an essential task in E-commerce and has a crucial impact on making informed business decisions. It can help us to manage the workforce, cash flow and resources such as optimizing the supply chain of manufacturers etc. Sales forecast is a challenging problem in that sales is affected by many factors including promotion activities, price changes, and user preferences etc. Traditional sales forecast techniques mainly rely on historical sales data to predict future sales and their accuracies are limited. Some more recent learning-based methods capture more information in the model to improve the forecast accuracy. However, these methods require case-by-case manual feature engineering for specific commercial scenarios, which is usually a difficult, time-consuming task and requires expert knowledge. To overcome the limitations of existing methods, we propose a novel approach in this paper to learn effective features automatically from the structured data using the Convolutional Neural Network (CNN). When fed with raw log data, our approach can automatically extract effective features from that and then forecast sales using those extracted features. We test our method on a large real-world dataset from CaiNiao.com and the experimental results validate the effectiveness of our method.

Six-year-old Jamil starts school on September 11. There will be no ISIS fighters in his first grade class in Ulm, Germany, but Jamil, haunted by nightmares, is still fighting the ISIS demons. The boy's ordeal began in northern Iraq on August 3, 2015. Then four-years-old, he was one of many Yazidis captured by ISIS, crammed into a bus, and taken to Mosul, the second largest city in Iraq, then under ISIS control. The Yazidi people are an ancient, non-Muslim religious community regarded by radical Islamists as infidels worthy of death.

Lipo Wang's research interests are in computational intelligence, i.e., neural networks, evolutionary computation, and fuzzy systems, with applications to multimedia, bioinformatics, and data mining. He has published over 50 journal publications, 14 books (authored/edited), 70 conference presentations, and 7 book chapters. He holds a U.S. patent on a neural network for image sequence processing. He is an Associate Editor / Editorial Board member for 7 international journals, including IEEE Transactions on Neural Networks, IEEE Transactions on Evolutionary Computation. He is Chair of the Emergent Technologies Technical Committee, IEEE Neural Networks Society.

Have you ever imagined your city being taken over by an army of robots? This has just happened in China, expect the robots were there for a dance party. Engineers in Guangzhou gathered more than 1,000 droids on August 17 and programmed them to dance at the same time. The adorable little robots, known as Dobi, shook their bodies, stretched their arms and tapped their feet simultaneously during the spectacular performance in front of the Guangzhou Baiyun International Convention Centre. A total of 1,069 Dobi robots took over the dance floor as they grooved in perfect synchronisation.

To start with, AI really is a big deal. The Harvard Business Review calls it, "the most important general-purpose technology of our era." According to some pundits, AI could contribute up to US$15.7 trillion to the global economy in 2030 – or more than the current output of China and India combined." Many companies have seen the opportunity and the investments are flowing in. According to McKinsey1, tech giants have already invested 20-30 billion dollars in AI technology.

In our recent series of blog posts on Topic Models, we've tried to explore this powerful new resource in the BigML Dashboard, in the API, using WhizzML, and we have also suggested some uses for it. But we've left a nuts and bolts description of how Latent Dirichlet Allocation (LDA) works until the end. Within this post, the last of a series of six posts, we'll try here to give you exactly that: A high-level overview of the internal mathematics that underlies Topic Models, and what that mathematics might imply for you, the modeler. While I'll explain a few things here, a more precise and technical explanation given by the inventor of the technique, David Blei, is available. Where there seems to be conflict between his explanation and mine, rest assured, his is correct!

Over the last year, there have been a growing number of media reports on Chinese advances in artificial intelligence (AI), as well a state-led push to boost the industry. The results: "China lags far further behind than many had imagined." In related news, Reuters says that internet giant Baidu, one of China's leading AI firms, will form a "7 billion yuan ($1 billion) private equity fund together with China Life Insurance Group, one of the country's biggest insurers. The find will focus on "unlisted companies with'significant association;' with China, in the internet sector, including mobile internet, artificial intelligence, and internet finance." For more on AI in China, listen to these Sinica Podcast episodes with Kai-fu Lee 李开复 and Andrew Ng.

When we were in the city of Danyang, China, we witnessed a real-life paradox. Danyang is best known for its explosive growth in optical lens manufacturing over the last decade, sprouting hundreds of factories with cleanrooms chock-full of gleaming, automated machinery. There is a lot that goes into manufacturing a lens, and this machinery performs the bulk of it: from lens curing, lens cleaning, to lens coating. As Stanford AI researchers and engineers wildly interested in Chinese manufacturing, we were impressed by this caliber of automation. But the paradox greeted us as soon as we walked into the rooms responsible for the most critical part of the entire process: quality control.

Google is rolling out a flurry of products in Indonesia. Chief among the new additions are YouTube Go and Google Assistant. The announcements (made at its second annual Google for Indonesia event) tie into the web giant's plan to get its apps to the "next billion" internet users. Until now, this strategy has mainly focused on India. But, it seemed inevitable that Google would expand its reach to more emerging (mobile-first) countries.

There are industry gatherings for all sectors, and that includes the funeral sector. It's not an area where you'd expect to find many tech products, but at the Tokyo International Funeral & Cemetery Show 2017 this week, all eyes were on the latest breakthrough in Buddhist priests. That's very expensive, so plastic molding company Nissei Eco Co. had an idea: create a robotic Buddhist priest and undercut the real thing on price. And rather than starting from scratch, Nissei instead modified an existing robot in the form of SoftBank's Pepper robot. As Hannah Gould, a researcher at the Japan Foundation, points out in the video above, Japan and technology have been evolving at the same time so a robot priest won't seem too weird. All Nissei had to do to modify the Pepper robot was write some software allowing it to tap the drums while it chanted.