Flexible Models for Microclustering with Application to Entity Resolution

Neural Information Processing Systems

Most generative models for clustering implicitly assume that the number of data points in each cluster grows linearly with the total number of data points. Finite mixture models, Dirichlet process mixture models, and Pitman-Yor process mixture models make this assumption, as do all other infinitely exchangeable clustering models. However, for some applications, this assumption is inappropriate. For example, when performing entity resolution, the size of each cluster should be unrelated to the size of the data set, and each cluster should contain a negligible fraction of the total number of data points. These applications require models that yield clusters whose sizes grow sublinearly with the size of the data set. We address this requirement by defining the microclustering property and introducing a new class of models that can exhibit this property. We compare models within this class to two commonly used clustering models using four entity-resolution data sets.

How General Motors And IBM Watson Will Personalize The Driving Experience - ARC


The utopia of driverless cars may still be out of reach, but General Motors wants to ensure that today's vehicles provide a unique or individual experience. The carmaker has partnered with IBM to develop what GM calls a "cognitive mobility platform" that will deliver personalized content while on the road. The partnership brings together GM's connected vehicle system OnStar with IBM's learning supercomputer Watson in the form of a platform called OnStar Go. According to a press release, OnStar Go is the auto industry's first such cognitive computing platform and will give drivers the opportunity to connect or interact with their favored brands while behind the wheel. Or to put it another way, the platform will make sure the driver makes the most of her or his time in the car.

IBM Watson drives 3D-printed autonomous bus around Washington DC


IBM has teamed up with an electric vehicle company to put its Watson artificial intelligence into a driverless electric bus. Dubbed Olli, the autonomous vehicle will be used to take passengers around Washington DC, and is the brainchild of Local Motors, the Arizona-based automaker. It said its bus is the first vehicle to use IBM Watson's car-focused cognitive learning platform, Watson Internet of Things (IoT) for Automotive. Local Motors unveiled the bus at its new facility in National Harbor, Maryland, 12 miles from the US capital. The bus itself is 3D-printed and can carry up to 12 people and is powered by an electric motor.

Saatchi LA Trained IBM Watson to Write Thousands of Ads for Toyota


The Mirai is Toyota's car of the future. It runs on hydrogen fuel cells, gets 312 miles on a full tank and only emits water vapor. So, to target tech and science enthusiasts, the brand is running thousands of ads with messaging crafted based on their interests. The campaign was written by IBM's supercomputer, Watson. After spending two to three months training the AI to piece together coherent sentences and phrases, Saatchi LA began rolling out a campaign last week on Facebook called "Thousands of Ways to Say Yes" that pitches the car through short video clips.

Here's What IBM Watson Will Be Doing in GM's Cars


General Motors gm and International Business Machines ibm on Tuesday said they would combine IBM's artificial intelligence software Watson with the carmaker's OnStar system in order to market services to drivers in their vehicles. The feature, called OnStar Go, is set to debut early next year in more than 2 million GM vehicles with 4G service, IBM and GM said in a joint statement. IBM's Watson, which beat two previous winners of the quiz show "Jeopardy!" in 2011, will sift through data in order to recognize a driver's habits, allowing third-party marketers to deliver targeted offers, whether nearby coffee shops, reminders about shopping-list items, or paying for fuel from their dashboards. Carmakers have been adding connected services into their vehicles to duplicate the convenience of smartphones, which can suggest nearby restaurant offers, or point the way to a gas station. Data generated from connected vehicles is valuable to automakers, although some consumers have been wary of privacy and data security issues.