Collaborating Authors


Listen to deepfake Gucci Mane read classic literature


Mark Twain once said that the mark of a classic is that everyone wants to have read it but not actually read it. It makes sense: Classics must provide some artistic or cultural value to be considered "classic" -- but they're just so boring. MSCHF just made the Western canon more exciting with Project Gucciberg. It's Project Gutenberg (a collection of public domain Western literature) meets the rapper Gucci Mane. Using Artificial Intelligence, MSCHF recreated his voice to read classics from Pride and Prejudice to Don Quixote.

[R] Generative Adversarial Transformers (2103.01209)


Abstract: We introduce the GANsformer, a novel and efficient type of transformer, and explore it for the task of visual generative modeling. The network employs a bipartite structure that enables long-range interactions across the image, while maintaining computation of linearly efficiency, that can readily scale to high-resolution synthesis. It iteratively propagates information from a set of latent variables to the evolving visual features and vice versa, to support the refinement of each in light of the other and encourage the emergence of compositional representations of objects and scenes. In contrast to the classic transformer architecture, it utilizes multiplicative integration that allows flexible region-based modulation, and can thus be seen as a generalization of the successful StyleGAN network. We demonstrate the model's strength and robustness through a careful evaluation over a range of datasets, from simulated multi-object environments to rich real-world indoor and outdoor scenes, showing it achieves state-of-the-art results in terms of image quality and diversity, while enjoying fast learning and better data-efficiency.

Photos of Amelia Earhart, Marie Curie and others come alive (creepily), thanks to AI


Artificial intelligence (AI) can now transform photos of people into short, highly realistic animations, much like the moving pictures in the newspapers and posters of Harry Potter's magical world. In these AI-animated clips, faces that were once frozen in time blink, turn their heads and even smile, their movements wavering between astonishingly lifelike and deeply unsettling (and yes, downright creepy). Genealogy website MyHeritage introduced the animation engine on Feb. 25. Developed by technology company D-ID and known as Deep Nostalgia, it enables users to animate photos via the MyHeritage website, representatives said in a blog post. D-ID designed custom algorithms that recreate the naturalistic movement of human faces digitally, applying those subtle movements to photographs and modifying facial expressions that move as human faces normally do, according to the D-ID website.

[D] Simple Questions Thread December 20, 2020


Hi, I'm working in a museum, currently trying to optically characterize a big historic lens. Unfortunately, it is mounted in a device which can't really be taken apart (issues of conservation), so conventional methods are rather hard to do. I've been loosely following the advances in neural network based approaches ("Two minute papers" kinda stuff) and was wondering if anyone has already realized a solution to my problem using machine learning or similar techniques. That is: Print out a defined optical pattern (like a QR code), "wave" it on one side of the lens and record the image with a camera on the other to get a 3D model of the lens in the end. In my head, it should be possible to train a network using conventional light simulation of randomly generated glass bodies.

Artificial Intelligence Vs. Machine Learning - AI Summary


Machine learning is a type of artificial intelligence, but it's not the style and kind of A.I. While artificial intelligence is a measure of a computer's intellectual ability, machine learning is a type of artificial intelligence used to build intellectual ability in computers. Today, IBM offers a service called IBM Watson Machine Learning that allows third parties to use their technology to build, train, and test predictive software like the kind used by the Watson supercomputer, which needed the ability to independently'understand' and'respond' to human writing and speech. Watson the supercomputer is artificial intelligence, while Watson's ability to'understand' language and respond using it is machine learning, much the same kind a digital assistant like Alexa uses to be able to talk to you. Artificial intelligence as we most often see it in the movies is much more advanced than IBM's Watson, but machine learning will be an essential component of higher-level A.I., like proper robots and androids, just as it's an important component of Watson.

AI: The next enabler of media, journalism, and content creation?


In a digital world overloaded with content and short on resources, reaching and engaging new audiences has been a persistent challenge for creative industries. Some top media players have turned to artificial intelligence (AI) for a possible solution. But the adoption of AI-powered technologies in the media has been slow compared to its uptake in other sectors, she said, speaking at an online event organized by the European Broadcasting Union's AI and Data Initiative (AIDI). Lack of resources, limited understanding, and the low number of use cases to date continue to hold back media AI use, she added. The AI Maturity Model produced by digital consultancy Gartner shows the media using AI mostly on active and operational levels.

[D] support set concept in Machine learning and one shot learning


In many papers like " Matching Networks for One Shot Learning " support set of images play a big role. However, I have trouble understanding what support set is? My understanding is- If I have trained my model on classes-"cat" and "dog". So during training my support set will have images of cats and dogs. But when at time of testing I wanted to see if image of " Horse" is there in image of support set or not. So can my support set have new image class(horse here). During testing time can I use this kind of 1 shot network to find my test image in collection of support image given while inference?

Robot Dogs: New cops with artificial intelligence patrol the streets of New York


"This robot is capable of using Artificial intelligence To move between things, and very complex environments, "added NYPD Depot John.