Temporal point process is an expressive tool for modeling event sequences over time. In this paper, we take a reinforcement learning view whereby the observed sequences are assumed to be generated from a mixture of latent policies. The purpose is to cluster the sequences with different temporal patterns into the underlying policies while learning each of the policy model. The flexibility of our model lies in: i) all the components are networks including the policy network for modeling the intensity function of temporal point process; ii) to handle varying-length event sequences, we resort to inverse reinforcement learning by decomposing the observed sequence into states (RNN hidden embedding of history) and actions (time interval to next event) in order to learn the reward function, thus achieving better performance or increasing efficiency compared to existing methods using rewards over the entire sequence such as log-likelihood or Wasserstein distance. We adopt an expectation-maximization framework with the E-step estimating the cluster labels for each sequence, and the M-step aiming to learn the respective policy. Extensive experiments show the efficacy of our method against state-of-the-arts.

We consider the problem of generating plausible and diverse video sequences, when we are only given a start and an end frame. This task is also known as inbetweening, and it belongs to the broader area of stochastic video generation, which is generally approached by means of recurrent neural networks (RNN). In this paper, we propose instead a fully convolutional model to generate video sequences directly in the pixel domain. We first obtain a latent video representation using a stochastic fusion mechanism that learns how to incorporate information from the start and end frames. Our model learns to produce such latent representation by progressively increasing the temporal resolution, and then decode in the spatiotemporal domain using 3D convolutions. The model is trained end-to-end by minimizing an adversarial loss. Experiments on several widely-used benchmark datasets show that it is able to generate meaningful and diverse in-between video sequences, according to both quantitative and qualitative evaluations.

Accurate entity linkers have been produced for domains and languages where annotated data (i.e., texts linked to a knowledge base) is available. However, little progress has been made for the settings where no or very limited amounts of labeled data are present (e.g., legal or most scientific domains). In this work, we show how we can learn to link mentions without having any labeled examples, only a knowledge base and a collection of unannotated texts from the corresponding domain. In order to achieve this, we frame the task as a multi-instance learning problem and rely on surface matching to create initial noisy labels. As the learning signal is weak and our surrogate labels are noisy, we introduce a noise detection component in our model: it lets the model detect and disregard examples which are likely to be noisy. Our method, jointly learning to detect noise and link entities, greatly outperforms the surface matching baseline. For a subset of entity categories, it even approaches the performance of supervised learning.

MOSCOW - Russia said on Monday it had added the popular dating app Tinder to a list of entities obliged to hand over user data and messages to law enforcement agencies on demand, including the main successor agency to the Soviet-era KGB. Roskomnadzor, Russia's telecoms and media regulator, said in a statement that Tinder had been added to its special register at the end of last month after providing the requisite information to allow itself to be added. The move, part of a wider Russian drive to regulate the internet, means that Tinder will be obliged to store users' metadata on servers inside Russia for at least six months as well as their text, audio or video messages. Russia's law enforcement agencies such as the FSB security service, which took over most of the KGB's functions, can require companies on the register to hand over data on demand. The Russian state's increased regulation of the internet has drawn criticism from some opposition politicians and sparked protests from campaigners who are concerned about what they say is creeping Chinese-style control of the online world.

The role artificial intelligence plays in the information Australians have access to needs transparency and regulatory oversight to mitigate "filter bubbles" – where people aren't challenged by alternative viewpoints – and other adverse outcomes. Algorithmic control over news and information, via Google Search and Facebook Newsfeed, is one of the key focus points for industry lobbying Free TV in its submission to the Department of Industry, Innovation and Science's discussion paper on Artificial Intelligence: Australia's Ethics Framework. AI has a growing role in how humans access content. Artificial intelligence will play an increasingly important role in everyday lives as inventions such as driverless cars become more of a reality. However, the department notes an AI ethics framework is not about changing laws or ethical standards, it is about making sure those already existing can be applied to AI. "The point of this submission was there is this whole area that's very important to the fabric of society, which is news, and that wasn't something that was focused on in the paper," Free TV chief executive Bridget Fair said.

As a rule, the more medications an individual patient takes, the greater the risk of suffering a negative side effect. Thus, there is a delicate balance between the clinical benefit of the medications, and the risk to harm as an aggregate, necessitating continuous evaluation of each medication, making sure harm does not outweigh the benefit. Yet, the hunger for medications in the U.S. is growing with no end in sight. In a Consumer Reports study conducted in 2017, while the US population had only increased by 21 percent over the past two decades, there is a shocking 85 percent increase in the number of filled prescriptions, with more than half of the US population on a prescription medication. A typical American is prescribed up to four medications on average, not including over-the-counter drugs, creating complex medication scenarios and increasing the likelihood of an ADEs.

Television news coverage brings to mind images of newsreaders in studios, reporters in the field, previously recorded footage and rapid-fire barrages of vivid advertising imagery. This raises the question of just how long a typical "shot" lasts and whether there are substantial differences between television news stations. Using the "Shot Change" detection feature of Google's Video AI platform to analyze a week of television news, what new insights could we learn about the speed at which television news narratives move? Google's Video AI API brings the company's image analysis algorithms to the world of video. While in the past videos had to be split into frames and analyzed as still images, the Video AI API enables videos to be analyzed natively, enabling time-based analysis like detecting shot changes.

Clay discovered on Mars that formed when soil mixed with water may give crucial clues to life that once lived on the now-barren planet billions of years ago. NASA's six-wheeled Curiosity rover has discovered the material on the martian surface beforehand - but never in such large quantities. Curiosity marked the occasion with an impressive selfie via its Mars Hand Lens Imager (MAHLI), a camera on the end of the rover's robotic arm. NASA's six-wheeled robot has found clay on the martian surface beforehand but never before in such large quantities. It was also marked with an impressive selfie of the Curiosity rover via its Mars Hand Lens Imager (MAHLI), a camera on the end of the rover's robotic arm (pictured) The momentous discovery was made in an area aptly known as the'clay-bearing unit' on the incline at the base of Mount Sharp, a 3.4 mile-high (4.5km) mountain.

A newly launched investigation could finally get to the bottom of a mystery that has baffled scientists since the 1950s. For decades, scientists have observed brief flashes of light that appear on the surface of the moon several times a week. But, no one knows exactly what's causing them. Now, using a specially designed lunar telescope in Spain that boasts two cameras, a team will keep an eye on the moon's activity every night in hopes to capture these strange phenomena and ultimately pinpoint the source. For decades, scientists have observed brief flashes of light that appear on the surface of the moon several times a week.

A driverless train that injured 14 people in Yokohama on Saturday after moving in the wrong direction continued moving for 1 meter even after hitting a buffer at a station because of the way the buffer works, the train operator said Monday. Saturday's accident occurred at Shin-Sugita station on the Kanazawa Seaside Line. Of the 14 passengers hurt, six sustained serious injuries. According to the operator, Yokohama Seaside Line Co., the unmanned train traveled for 25 meters in the wrong direction, hit the buffer, which is designed to absorb any impact, and then continued to move for about a meter. The Japan Transport Safety Board and the operating company are specifically investigating the circumstances of the accident, and believe that the impact was magnified when the moving train hit the buffer.