Collaborative filtering (CF) has been successfully employed by many modern recommender systems. Conventional CF-based methods use the user-item interaction data as the sole information source to recommend items to users. However, CF-based methods are known for suffering from cold start problems and data sparsity problems. Hybrid models that utilize auxiliary information on top of interaction data have increasingly gained attention. A few "collaborative learning"-based models, which tightly bridges two heterogeneous learners through mutual regularization, are recently proposed for the hybrid recommendation. However, the "collaboration" in the existing methods are actually asynchronous due to the alternative optimization of the two learners. Leveraging the recent advances in variational autoencoder~(VAE), we here propose a model consisting of two streams of mutual linked VAEs, named variational collaborative model (VCM). Unlike the mutual regularization used in previous works where two learners are optimized asynchronously, VCM enables a synchronous collaborative learning mechanism. Besides, the two stream VAEs setup allows VCM to fully leverages the Bayesian probabilistic representations in collaborative learning. Extensive experiments on three real-life datasets have shown that VCM outperforms several state-of-art methods.

Trains are part-and-parcel of every day lives in countries with large, diverse, multi-lingual population like India. Consequently, an assistant which can accurately predict and explain train delays will help people and businesses alike. We present a novel conversation agent which can engage with people about train status and inform them about its delay at in-line stations. It is trained on past delay data from a subset of trains and generalizes to others.

Almost every day I make a pot of tea. Strong, black tea, the kind you have to steep properly in a ritual that involves a kettle, a tea tin, tea lights, a tea cozy. It's a four-minute brew, so I set a timer. I used to do it on the microwave, but some time ago I just started asking Alexa, via the Amazon Echo on my kitchen counter. "Alexa, set a timer for four minutes."

The insurance industry – one of the least digitalized – is not surprisingly one of the most ineffective segments of the financial services industry. Internal business processes are often duplicated, bureaucratized, and time-consuming. As the ubiquity of machine learning and artificial intelligence systems increases, they have the potential to automate operations in insurance companies thereby cutting costs and increasing productivity. However, organizations have plenty of reasons to resist the AI expansion; the fear of unemployment and the lack of trust in cognitive systems are among them. But these are hardly justified concerns.

I can't profess to fully understand all of the complexities of localizing services for various languages, nuances, accents and dialects where voice recognition is concerned. However, with Amazon's Alexa ambitions ramping up after its hardware event Thursday, it's worth questioning why the voice assistant's language support is so abysmal. Almost four years after launching, Alexa supports English, French, German and Japanese, with Italian and Spanish on the way. Compare that with Siri, which, within a year of launch, supported all of the above languages, along with Korean, Mandarin and Cantonese -- and some languages were tuned for local differences by that point, too. Apple's voice assistant is now available in 21 languages.

Feedly's discovery tool helps you explore topics and sources in different ways. If you search for a topic, we show you related topics to dive deeper. If you follow a new source, we recommend other sources to pair with it. We produce those recommendations with a collaborative filtering technique called item2vec. This blog post gives you more information on how we achieved this.

To use the title of Brad Stone's seminal book about the nation's largest online retailer, Amazon is so much "The Everything Store" that it can be a little hard to remember when it was just a bookstore. But Jeff Bezos' ambitions are actually the grandest in the land, and the dozen-plus Alexa devices the company announced today show the next step. Throughout tech history, incumbents have needed to beware of leapfroggers. Apple never needed to defend a dumb-phone business, so it could upend smartphones. T-Mobile had no landline thinking, so it could become the UnCarrier.

The Alexa-powered Amazon microwave you didn't ask for is here. The company's big hardware splurge encompasses your car, your kitchen and even your walls. There's upgraded Echo devices, too, if that's what you were looking for. Meanwhile, Apple's iOS 12 is an update worth your time, and life insurance companies are very interested in your step count. The company announced not one, not two, but seven new Echo products at an event in Seattle.

Microsoft and Amazon said that voice and video calls via the service will come to Alexa devices (including Microsoft's Xbox One) with calls that you can start and control just by voice. Last year the two companies announced plans to make Alexa and Cortana work together and it's taken a while to arrive, but now it's here. Amazon's push to make people buy more things via its assistant could provide a boost to Microsoft's aspirations of product integration in a way that didn't happen after the launch of the Xbox One and Kinect, which already featured voice control for Skype before Cortana and Alexa were on the scene.

Amazon took a major shot at smart speaker rival Sonos, unveiling all the elements for a complete Alexa-enabled sound system including a slew of new Echo devices for the home and vehicles, along with updates to its Alexa artificial intelligence (AI) assistant. At an event in the US, the company announced audio equipment including the $130 Echo Sub (pictured), a 6-inch subwoofer which can be paired with other Amazon Echo devices to improve sound. It also unveiled Alexa-enabled amplifiers, the $200 Echo Link and $300 Echo Link Amp, to fine tune and boost sound quality in existing stereo equipment; as well as the $35 Echo Input, a plug-in device with four-microphones which adds Alexa to existing speakers. The company also rolled out revamped versions of its staple Echo smart home hub series, including: Echo Show ($230), redesigned with a larger 10-inch display, upgraded speaker system and integration with new content players including Hulu; Echo Plus ($150), featuring a new fabric exterior, a built-in Zigbee hub to connect compatible IoT devices, upgraded speakers and a temperature sensor; and Echo Dot ($50), also with an updated mesh fabric and better speakers. Amazon's effort to bring Alexa to as many devices as possible included the debut of the Echo Wall Clock ($30) to provide a visual display for timers, alarms and reminders; and the company's first smart plug ($25), which is essentially an Alexa-enabled timer.