Segmentation of pancreas is important for medical image analysis, yet it faces great challenges of class imbalance, background distractions and non-rigid geometrical features. To address these difficulties, we introduce a Deep Q Network(DQN) driven approach with deformable U-Net to accurately segment the pancreas by explicitly interacting with contextual information and extract anisotropic features from pancreas. The DQN based model learns a context-adaptive localization policy to produce a visually tightened and precise localization bounding box of the pancreas. Furthermore, deformable U-Net captures geometry-aware information of pancreas by learning geometrically deformable filters for feature extraction. Experiments on NIH dataset validate the effectiveness of the proposed framework in pancreas segmentation.

Consider a collaborative task that requires communication. Two agents are placed in an environment and must create a language from scratch in order to coordinate. Recent work has been interested in what kinds of languages emerge when deep reinforcement learning agents are put in such a situation, and in particular in the factors that cause language to be compositional-i.e. meaning is expressed by combining words which themselves have meaning. Evolutionary linguists have also studied the emergence of compositional language for decades, and they find that in addition to structural priors like those already studied in deep learning, the dynamics of transmitting language from generation to generation contribute significantly to the emergence of compositionality. In this paper, we introduce these cultural evolutionary dynamics into language emergence by periodically replacing agents in a population to create a knowledge gap, implicitly inducing cultural transmission of language. We show that this implicit cultural transmission encourages the resulting languages to exhibit better compositional generalization and suggest how elements of cultural dynamics can be further integrated into populations of deep agents.

Wish there was a place to shop where you could compare prices from multiple retailers at once and get the best deal on your favorite products, while also getting everything you need shipped quickly and efficiently right to your door? Say hello to Google Express, the online shopping service that's designed to give you that experience. While it's been around for years, this constantly evolving platform is part of Google's attempt to unseat Amazon's hegemony in the online shopping world. The service aims to make buying products online more convenient and accessible. But chances are, you've never even heard of it before.

The world's first footage of a black hole in motion could soon be created by the scientists behind a groundbreaking image of the phenomenon released last week. Experts using the Event Horizon Telescope (EHT) say they will produce a video of hot gases whirling chaotically around the shadow or'accretion disk' of the black hole. The supermassive black hole sits at the centre of the galaxy Messier 87, roughly 54 million light-years from Earth. EHT is a'virtual' telescope that uses data from observatories around the world to turn the whole of the Earth into one giant detector. Researchers believe that, as more telescopes join the EHT project, they can produce more detailed images and eventually film the black hole.

An 1,100-pound emergency robot helped to save a piece of human history during a blaze at Paris' Notre Dame cathedral that threatened to burn the historic monument to the ground. The formidable device, dubbed Colossus, a remote-controlled drone equipped with hoses and cameras, was able to roll its way into the cathedral to help fight the fire -- which burned through the structure's old wooden roof -- from within. Colossus, which is both fire-resistant, water-proof, and capable of carrying up to 1,200 pounds not only helped to stop the fire before it completely razed the structure, but reduced the need for fire fighters to enter the church where they would be in danger from falling debris. At the time, the cathedral was only 15 to 30 minutes away from being completely burned to the ground, reports say. Weighing in at 1,100 pounds, Colossus is a firefighting robot that can be controlled remotely.

A Japanese tech start-up is using deep learning to teach a pair of machines a simple job for a human, but a surprisingly tricky task for a robot - cleaning a bedroom. Though it may seem like a basic, albeit tedious, task for a human, robots find this type of job surprisingly complicated. A Japanese tech start-up is using deep learning to teach AI how to deal with disorder and chaos in a child's room. Deep learning is where algorithms, inspired by the human brain, learn from large amounts of data so they're able to perform complex tasks. Some tasks, like welding car chassis in the exact same way day after day, are easy for robots as it is a repetitive process and the machines do not suffer with boredom in the same way as disgruntled employees.

Researchers say they've successfully created a more powerful computer-like human cell that could eventually be used to help monitor one's health or even fight against cancer and other illnesses. Using the gene-editing tool CRISPR-Cas9, researchers were able to model a human cell after a computer and make what they are referring to as a'program scalable circuits.' 'This cell computer may sound like a very revolutionary idea, but that's not the case," said Martin Fussenegger, Professor of Biotechnology and Bioengineering at the Department of Biosystems Science and Engineering at ETH Zurich in Basel. 'The human body itself is a large computer. Its metabolism has drawn on the computing power of trillions of cells since time immemorial.'

Scientists have been able to partially revive the brains of decapitated pigs that died four hours earlier in a groundbreaking study. Experts used tubes that pumped a chemical mixture designed to mimic blood into the decapitated heads of 32 pigs to restore circulation and cellular activity. Echoing Mary Shelley's classic novel Frankenstein, billions of neurons began acting normally and the deaths of other cells was reduced over the course of six hours. Electrical brain activity across the brain associated with awareness, perception and other high level functions were not observed, however. While the find is an exciting breakthrough, it is still a long way from proof that a person's consciousness can be recovered after they die, experts caution.

The New York Times has confirmed what some have long suspected: The Chinese government is using a "vast, secret system" of artificial intelligence and facial recognition technology to identify and track Uighurs--a Muslim minority, 1 million of whom are being held in detention camps in China's northwest Xinjiang province. This technology allows the government to extend its control of the Uighur population across the country. It may seem difficult to imagine a similar scenario in the U.S., but related technologies, built by Amazon, are already being used by U.S. law enforcement agencies to identify suspects in photos and video. And echoes of China's system can be heard in plans to deploy these technologies at the U.S.-Mexico border. A.I. systems also decide what information is presented to you on social media, which ads you see, and what prices you're offered for goods and services.

It's common knowledge that Barack Obama met the woman who eventually became his wife, Michelle Robinson, when he came to work at her law firm as a summer associate. George W. Bush met the future Mrs. Bush, who was Laura Welch back then, at a barbecue and took her mini-golfing the next day. And we all remember that Bill and Hillary Clinton were law school sweethearts. The historical record is full of these president-and-first-lady origin stories: Harry Truman was just 6 when he met the woman he would go on to marry, in church. So it's only natural to ask how the current crop of presidential candidates' how-they-met stories stack up.