Collaborating Authors

Nvidia GANimal uses A.I. To Make Animals Smile in Pictures Digital Trends


Can't get your dog or that tiger at the zoo to smile for your Instagram? A new artificially intelligent program developed by researchers from Nvidia can take the expression from one animal and put it on the photo of another animal. Called GANimal -- after generative adversarial networks, a type of A.I. -- the software allows users to upload an image of one animal to re-create the pet's expression and pose on another animal. GAN programs are designed to convert one image to look like another, but are typically focused on more narrow tasks like turning horses to zebras. GANimal, however, applies several different changes to the image, adjusting the expression, the position of the animal's head, and in many cases, even the background, from the inspiration image onto the source image.

Sick of dog pictures on social media? Nvidia's GANimal AI lets you turn them into other animals


Of course, I'm kidding, how can anybody get sick of dog pictures on Facebook? Nvidia's research teams have been doing some pretty crazy stuff with AI the last few years. This latest one is pretty funny from an amusement level standpoint but quite groundbreaking from a technical one. It's a challenging task for computers, although it has been done in the past. Previously, though, it required many images in order to make it work.

NVIDIA's new AI lets you recreate your pet's smile on a lion


NVIDIA, the company behind some of the most impressive graphics cards, has pulled off yet another machine learning-powered wizardry. Researchers from the Santa Clara-based chipmaker have created a new AI tool -- dubbed Ganimal -- that can take in a picture of an animal and recreate its facial expression and pose on the face of any other creature. In a paper -- titled "Few-Shot Unsupervised Image-to-Image Translation" aka FUNIT -- the image-to-image translation method leverages generative adversarial networks (GANs), a neural network that has been widely adopted in a variety of image generation and transfer scenarios. You can give the tool a spin right here and read the technical aspects of the research here. "In this case, we train a network to jointly solve many translation tasks where each task is about translating a random source animal to a random target animal by leveraging a few example images of the target animal," Ming-Yu Liu, the lead computer vision researcher behind FUNIT, said.

Ever wonder what you'd look like as a dog? Bizarre new AI can transform subjects into other SPECIES

Daily Mail - Science & tech

A new machine learning algorithm is expanding the world of deep-faked images by morphing pictures of pets and even human faces into other species. In a demonstration and corresponding research paper, a new algorithm developed by Nvidia -- a project that is aptly dubbed'Petswap' -- shows how an AI can take the concept of an animal (i.e. a person's pet) and extrapolate that idea to envision other animals. Petswap, besides just being a generally fun experiment, is helping to teach algorithms the important, but distinctly human, concept of'similar but different.' Here Nividia's algorithm is shown translating an image of a ferret across species, including big cats, canines, and a strikingly similar analog, the mongoose'Humans are remarkably good at generalization,'reads the researchers paper on arXiv, a preprint journal. 'When given a picture of a previously unseen exotic animal, say, we can form a vivid mental picture of the same animal in a different pose, especially when we have encountered (images of) similar but different animals in that pose before.'

A Heuristic Search Algorithm Using the Stability of Learning Algorithms in Certain Scenarios as the Fitness Function: An Artificial General Intelligence Engineering Approach Artificial Intelligence

This paper presents a non-manual design engineering method based on heuristic search algorithm to search for candidate agents in the solution space which formed by artificial intelligence agents modeled on the base of bionics.Compared with the artificial design method represented by meta-learning and the bionics method represented by the neural architecture chip,this method is more feasible for realizing artificial general intelligence,and it has a much better interaction with cognitive neuroscience;at the same time,the engineering method is based on the theoretical hypothesis that the final learning algorithm is stable in certain scenarios,and has generalization ability in various scenarios.The paper discusses the theory preliminarily and proposes the possible correlation between the theory and the fixed-point theorem in the field of mathematics.Limited by the author's knowledge level,this correlation is proposed only as a kind of conjecture.