The fall 2018 parade of new hardware continued last week when Amazon kicked open the cages at the Alexa zoo and let loose more than a dozen new smart home products--including an Echo device for your car. And while Amazon was the biggest news last week, it wasn't the only thing in the tech world worth talking about. Here's what you might have missed. This week on the Last Week in Tech podcast, we take a look into the current trend of retro gaming consoles and talk about some of our favorite classic titles while the other hosts make fun of my pathetic Punch Out skills.

They might be competing AI's from giant companies, but Alexa and Google still play nice together. A link has been sent to your friend's email address. A link has been posted to your Facebook feed. They might be competing AI's from giant companies, but Alexa and Google still play nice together.

Google looks to make a big splash at the 2018 Consumer Electronics Show, touting the Google Assistant. Apple TV has Siri, Amazon's Fire TV has Alexa, and now, Roku has joined forces with the Google Assistant to bring an established voice to its popular streaming players and branded TVs. Roku, the No. 1 streaming player, had offered its own voice search, but Google's Assistant, generally accessed via Google Home speakers, is more widely used by the public. Roku, in announcing new products for the fall Monday, didn't specify a time frame for the change, only saying it would be "soon," and for most existing devices. Additionally, the Roku TVs will have more functionality with Google, allowing viewers to say "Hey, Google," to turn their TV on and off, turn up the volume, mute, switch inputs and change channels, but only if the set is connected to an antenna.

With the availability of vast amounts of user visitation history on location-based social networks (LBSN), the problem of Point-of-Interest (POI) prediction has been extensively studied. However, much of the research has been conducted solely on voluntary checkin datasets collected from social apps such as Foursquare or Yelp. While these data contain rich information about recreational activities (e.g., restaurants, nightlife, and entertainment), information about more prosaic aspects of people's lives is sparse. This not only limits our understanding of users' daily routines, but more importantly the modeling assumptions developed based on characteristics of recreation-based data may not be suitable for richer check-in data. In this work, we present an analysis of education "check-in" data using WiFi access logs collected at Purdue University. We propose a heterogeneous graph-based method to encode the correlations between users, POIs, and activities, and then jointly learn embeddings for the vertices. We evaluate our method compared to previous state-of-the-art POI prediction methods, and show that the assumptions made by previous methods significantly degrade performance on our data with dense(r) activity signals. We also show how our learned embeddings could be used to identify similar students (e.g., for friend suggestions).

Complementary products recommendation is an important problem in e-commerce. Such recommendations increase the average order price and the number of products in baskets. Complementary products are typically inferred from basket data. In this study, we propose the BB2vec model. The BB2vec model learns vector representations of products by analyzing jointly two types of data - Baskets and Browsing sessions (visiting web pages of products). These vector representations are used for making complementary products recommendation. The proposed model alleviates the cold start problem by delivering better recommendations for products having few or no purchases. We show that the BB2vec model has better performance than other models which use only basket data.

If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA Today's newsroom and any business incentives. What better time to take stock of what you might need and hunt for a good price online? I don't know about you, but it's a lot easier for me to be patient about what I buy when I can do some from the comfort of my bed or loveseat. We sift through Amazon's daily and Gold Box deals every day to find the best ones: this weekend, you can save on a Matein laptop backpack, Amazon's Echo Show device, a woodsy essential oil diffuser, and more.

What changes will AI bring to your sales team? Do we really need this technology to navigate today?s market? Artificial Intelligence (AI) typifies the love-hate relationship that many people have with technology. They love the ease of using voice-controlled assistants like Siri and Alexa, but they don?t fully trust whatever is making it work. They have no problem with using chatbots and self-checkout lanes, but they baulk at the idea of?robots?

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."