Snippets of Lady Gaga's new album Joanne have been shared online after fans "tricked" Amazon's virtual assistant into playing preview clips. Previews can commonly be heard on Amazon when an album is available for pre-order, but they had been disabled for Gaga's highly-anticipated comeback. Owners of Amazon's Echo speaker then discovered they could access songs by issuing the instruction: "Play Joanne by Lady Gaga." The 30-second clips have been recorded and shared online by several fans, with one video showing Amazon's speaker lighting up and responding to the voice commands. Among the leaked songs are Hey Girl, in which Gaga duets with Florence Welch of Florence The Machine over a stomping, staccato piano line reminiscent of Elton Johns's Benny and the Jets.

My data is 64 x 64 images. I have tried the obvious approach of training the whole autoencoder end-to-end, but I could not get good reproductions as I decreased the feature vector length.

This is basically the same setting as semantic segmentation so any architecture that solves this problem can be adapted for your application. You can have a look at papers like U-Net, or Fully Convolutional Neural Networks, whose implementations are available for Caffe (I would also be surprised if there weren't re-implementations in other frameworks like TensorFlow or Theano). On a side note, I am personally using the very naive approach that you are describing (extracting patches around each pixel) and I have found that the performance loss is not that critical for my application. It might still be a good idea for you to try it anyway before switching to more "exotic" architectures.

For actress/singer/director Connie Stevens, it's always been about "me and the girls" -- her actress daughters Joely and Tricia Leigh Fisher from her short-lived marriage to singer Eddie Fisher. "They've always been the light in my eye," said Stevens, 78. "And I have found the older I get, that's really what counts anyway." And her daughters, who were just toddlers when she divorced Fisher in 1969, went with her when she performed in Las Vegas or made a movie -- Eddie Fisher, who battled substance abuse for years, wasn't part of their lives when they were growing up. And it wasn't too long before the Fisher girls would join their mom on stage.

At Oculus Connect 2 last year, Epic Games' Bullet Train demo stole the show -- leaning heavily on the "bullet time" effect popularized by the Matrix films to create a smooth, action-packed shooter that let players take down multiple enemies in slow motion. It had a neat gimmick: it used virtual reality to bend reality in a way we've only seen in the movies. The team brought the concept back to Oculus developer conference again this year as the heavily refined Robo Recall: a frantic, physics-based shooter with a sense of humor. Hands-down, it's one of the best Oculus Touch experiences I saw at the show. When it launches early next year, it will be absolutely free.

This article was originally published on The Conversation. For a sci-fi fan like me, fascinated by the nature of human intelligence and the possibility of building life-like robots, it's always interesting to find a new angle on these questions. As a re-imagining of the original 1970s science fiction film set in a cowboy-themed, hyper-real adult theme park populated by robots that look and act like people, Westworld does not disappoint. Westworld challenges us to consider the difference between being human and being a robot. From the beginning of this new serialisation on HBO we are confronted with scenes of graphic human-on-robot violence.

PREDICTING HOW artificial intelligence technology will evolve in the following ten or 20 years, or even beyond, is very difficult to say the least. However, certain is the fact that there is much to be gained to go around for everyone. It is estimated that by the year 2018, robots will literally be supervising more than three million of us at work; and by 2020, smart machines will become a major investment priority amongst at least 30% of all CIOs. As we speak many different fields spanning from customer service to journalism are already being set aside by increasingly able AI that can replicate human abilities and experience. Already before our eyes is an aspect that we once thought only belonged in future technology.

Wow. Very cool, anyone have any notes/summary?

In this latest University of Sydney'Open for Discussion' episode our host Dr Chris Neff speaks with Dr Michael Harre, lecturer in Complex Systems in the Faculty of Engineering and Information Technologies and artificial intelligence aficionado about where AI really is and how it is affecting our lives. Michael Harre will be appearing at Raise the Bar, Tuesday 18th October. Chris Neff: Welcome to Open for Discussion. Joining me today is Dr Michael Harre from the University's Faculty of Engineering and Information Technologies. Michael is an artificial intelligence aficionado, try saying that 3 times fast, and lecturer in complex systems. Chris Neff: Can I ask first, what is artificial intelligence and secondly, what got you into artificial intelligence? What was your background, how did you come to this? Ahh.. There's no straight forward answer in the sort of...general definition but usually it's something that runs on a computer that;s trying to do something kinda human like but perhaps not being very..very good at it. Because my understanding is mostly a star trek, star wars aahhhh... Will Smith movies and other kind of.. Dr Michael Harre: Ah yeah there's some great movies out there and the movies out there umm..they portray a combination of robot and ah..robots with some form of human like intelligence but umm..what you see in the robots is a bit more like um..what we think of as human behaviour and sort of expressing our human mind ah..but that's not what we are able to do at all with artificial intelligence yet.

When writing the screenplay for 1968's 2001, Arthur C. Clarke and Stanley Kubrick were confident that something resembling the sentient, humanlike HAL 9000 computer would be possible by the film's namesake year. That's because the leading AI experts of the time were equally confident. Clarke and Kubrick took the scientific community's predictions to their logical conclusion, that an AI could have not only human charm but human frailty as well: HAL goes mad and starts offing the crew. But HAL was put in an impossible situation, forced to hide critical information from its (his?) coworkers and ordered to complete the mission to Jupiter no matter what. "I'm afraid, Dave," says the robot as it's being dismantled by the surviving astronaut.