«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
«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».
«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
«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
«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
«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
«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
«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
«The AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains. Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi (Japanese chess) as well as Go».
Source : [1712.01815] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
«DL will not disagree with any data, will not figure out the injustices in the society, it’s just all “data to learn”. You should hire a dedicated human staff to create fake fair data of an ideal society where white people are arrested as often as blacks, where 50% of directors are women, and so on. But the cost of creating vast amounts of de-biased data edited by human experts, just to train a DL model, makes not worth to replace humans with AI in first place! Further, even if you had trained a DL model that really is fair, you have no evidence to convince a judge or a user about the fairness of any decision, since the DL will give no explanations».
Source : Deep Learning is not the AI future
© 2025 no-Flux
Theme by Anders Noren — Up ↑
