Étiquette : deep learning (Page 9 of 12)

26 février 2018 / noflux

«The most basic problem is that researchers often don’t share their source code. At the AAAI meeting, Odd Erik Gundersen, a computer scientist at the Norwegian University of Science and Technology in Trondheim, reported the results of a survey of 400 algorithms presented in papers at two top AI conferences in the past few years. He found that only 6% of the presenters shared the algorithm’s code. Only a third shared the data they tested their algorithms on, and just half shared « pseudocode »—a limited summary of an algorithm. (In many cases, code is also absent from AI papers published in journals, including Science and Nature.)».

Source : Missing data hinder replication of artificial intelligence studies | Science | AAAS

16 janvier 2018 / noflux

heart and AI

«The time between calling 911 and the ambulance arriving can be critical for saving heart attack victims, but the person on the phone may not know what’s happening: this AI parses non-verbal clues to help diagnose from a distance».

Source : Having A Heart Attack? This AI Helps Emergency Dispatchers Find Out

12 janvier 2018 / noflux

«Over a 10 week period the scientists showed images to human test subjects and recorded their brainwaves. At times the subjects brains were monitored in real-time while they were looking at the images, other times they were asked to “recall” the images. The researchers used the brain scans to train a deep learning network to “decode” the data and visualize what the person was thinking about».

Source : You think it and a robot sees it: The future is here with mind-reading AI

8 janvier 2018 / noflux

«We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations, and targeted because they can cause a classifier to output any target class. These adversarial patches can be printed, added to any scene, photographed, and presented to image classifiers; even when the patches are small, they cause the classifiers to ignore the other items in the scene and report a chosen target class».

Source : Adversarial Patch – Research Article | DeepAI

5 janvier 2018 / noflux

these images took about 18 days for the computers to generate

«Each of these images took about 18 days for the computers to generate, before reaching a point that the system found them believable»

Source : How an A.I. ‘Cat-and-Mouse Game’ Generates Believable Fake Photos – The New York Times

5 janvier 2018 / noflux

«Goodfellow’s friends were just as adamant that this method wouldn’t work, either. So when he got home that night, he built the thing. « I went home still a little bit drunk. And my girlfriend had already gone to sleep. And I was sitting there thinking: ‘My friends at the bar are wrong!' » he remembers. « I stayed up and coded GANs on my laptop. » The way he tells it, the code worked on the first try. « That was really, really lucky, » he says, « because if it hadn’t of worked, I might have given up on the idea. »»

Source : Google’s Dueling Neural Networks Spar to Get Smarter, No Humans Required | WIRED

5 janvier 2018 / noflux

«Arsenal’s smart assistant AI suggests settings based on your subject and environment. It uses an advanced neural network to pick the optimal settings for any scene (using similar algorithms to those in self driving cars). Like any good assistant, it then lets you control the final shot. Here’s how it works…»

Source : Meet Arsenal, the Smart Camera Assistant | Features

4 janvier 2018 / noflux

Tacotron 2

«You can listen to some of the Tacotron 2 audio samples that demonstrate the results of our state-of-the-art TTS system. In an evaluation where we asked human listeners to rate the naturalness of the generated speech, we obtained a score that was comparable to that of professional recordings».

Source : Research Blog: Tacotron 2: Generating Human-like Speech from Text

19 décembre 2017 / noflux

«Can we use AI to increase empathy for victims of far-away disasters by making our homes appear similar to the homes of victims?»

Source : Deep Empathy

11 décembre 2017 / noflux

«Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assumptions».

Source : Unsupervised Image-to-Image Translation Networks | Research

Étiquette : deep learning (Page 9 of 12)

Archives

Catégories

Méta