One of the drawbacks of frequent episode mining is that overwhelmingly many of the discovered patterns are redundant. Free-rider episode, as a typical example, consists of a real pattern doped with some additional noise events. Because of the possible high support of the inside noise events, such free-rider episodes may have abnormally high support that they cannot be filtered by frequency based framework. An effective technique for filtering free-rider episodes is using a partition model to divide an episode into two consecutive subepisodes and comparing the observed support of such episode with its expected support under the assumption that these two subepisodes occur independently. In this paper, we take more complex subepisodes into consideration and develop a novel partition model named EDP for free-rider episode filtering from a given set of episodes. It combines (1) a dual partition strategy which divides an episode to an underlying real pattern and potential noises; (2) a novel definition of the expected support of a free-rider episode based on the proposed partition strategy. We can deem the episode interesting if the observed support is substantially higher than the expected support estimated by our model. The experiments on synthetic and real-world datasets demonstrate EDP can effectively filter free-rider episodes compared with existing state-of-the-arts.

Despite the advancement of supervised image recognition algorithms, their de- pendence on the availability of labeled data and the rapid expansion of image categories raise the significant challenge of zero-shot learning. Zero-shot learn- ing (ZSL) aims to transfer knowledge from labeled classes into unlabeled classes to reduce human labeling effort. In this paper, we propose a novel self-training ensemble network model to address zero-shot image recognition. The ensemble network is built by learning multiple image classification functions with a shared feature extraction network but different label embedding representations, each of which facilitates information transfer to different subsets of unlabeled classes. A self-training framework is then deployed to iteratively label the most confident images in each unlabeled class with predicted pseudo-labels and update the ensem- ble network with the training data augmented by the pseudo-labels. The proposed model performs training on both labeled and unlabeled data. It can naturally bridge the domain shift problem in visual appearances and be extended to the generalized zero-shot learning scenario. We conduct experiments on multiple standard ZSL datasets and the empirical results demonstrate the efficacy of the proposed model.

I recently wrote about five technologies that are shaping the future of healthcare. One of these technologies -- artificial intelligence -- holds particular potential for improving medical care at the clinical level. Thanks to the digital revolution, medical professionals don't have to memorize nearly as much information as they did 50 years ago. Digital technology has liberated physicians, nurses and researchers to focus more mental energy on higher-level cognitive tasks and patient care. Artificial intelligence is poised to take this to the next level.

Noninvasive brain–computer interface (BCI) systems can restore functions lost to disability -- allowing for spontaneous, direct brain control of external devices without the risks associated with surgical implantation of neural interfaces. But as machine-learning algorithms have become faster and more powerful, researchers have mostly focused on increasing performance by optimizing pattern-recognition algorithms. But what about letting patients actively participate with AI in improving performance? To test that idea, researchers at the École Polytechnique Fédérale de Lausanne (EPFL), based in Geneva, Switzerland, conducted research using "mutual learning" between computer and humans -- two severely impaired (tetraplegic) participants with chronic spinal cord injury. The goal: win a live virtual racing game at an international event.

SikuliX is very unusual – a scripting/automation technology that relies on pattern matching, and is available for use via Python or Java. Developed at the User Interface Design Group at MIT, is a powerful and easy-to-use technology that uses image recognition to automate just about anything that appears on-screen. Sikuli is rather hard to slot – it offers all of the functionality of an automation or scripting tool, but it also offers some powerful and very novel image-matching functionality for truly novel use-cases that revolve around image search. In addition it has an OCR-mode, in which image matches are performed after converting those image patterns to text. This gives rise to some pretty new applications.

While the term "machine learning" generally relates to understanding structures or patterns in data, it can also refer to a very diverse set of activities and techniques. Most of us have experienced machine learning in our everyday lives with natural language processing (Alexa, Siri), image recognition (Facebook, Pinterest), purchase recommendations (Amazon) and search optimization (Google). These approaches generally use many different types of algorithms (e.g., neural networks, decision trees, clustering, support vector machines, etc.) Industrial operations, on the other hand, need more specialized approaches that can provide actionable insights to reduce downtime as well as improve throughput, operator safety, and product quality. Whether you call it Industry 4.0 or Industrial IoT or Digital Operations, the increased access to operational data, combined with the spread of computing, connectivity, and storage, has created the perfect environment for transforming industrial operations. The real opportunity is in unlocking the value of this data.

A wildly successful Kickstarter funded this Mammoth Interactive course. "It's simple and relaxing-- just what the doctor ordered." Enroll now to learn in-demand skills that employers are seeking. Data scientists make an average of $120,000 annually. With this course we will help get you there!

Botanicus Interacticus is a new interactive plant technology which does not require any new instrumentation in plants. A simple electrode placed inside the soil is able to grasp a ton of frequencies produced by the plant, converting it into a multi-touch gesture sensitive controller. Touché is a project developed at Disney Research which makes use of frequencies captured by sensing various events witnessed by the plant and simultaneously recognises complex human physical interactions with it. In simple words, it has the capability to express what kind of touch event has occurred -- caressing, pinching, holding, tickling, etc. Traditional capacitive sensors work by generating an electrical signal at a single frequency. This frequency is applied onto a conductive surface, such as a metal. The value of the capacitance changes if the hand is close enough to the surface of the plant or if it is in contact.

Google may have teased us with exciting new AR features for the Maps app, but it's not forgetting to make its Lens camera more useful, either. Since its launch last year, Lens has rolled out to iOS and gained a few skills, like identifying cat and dog breeds. At its I/O developer conference today, Google announced three new features for Lens -- Smart Text Selection, Style Match and Real-time results. After checking it out here at the show, I'm most intrigued by the text-recognition tools, which actually seem useful. What Smart Text Selection does is scan words in documents around you and let you interact with them in your phone.