Conscious that new generative AI art tools Midjourney, Dall-E 2 and Stable Diffusion may be as baffling for some as they are exciting for others, but nonetheless important and worth knowing about, here’s a short YouTube video explaining in simple terms what they can do, especially in a professional context, and, to an extent, how […]
A new AI-driven service called Deep Nostalgia from online genealogy company MyHeritage and using technology licensed from Israeli firm D-ID can animates portrait photos to create passable but fairly creepy fake video clips. It uses pre-recorded driver videos of facial movements and applies the one that best suits the image being manipulated. Users upload a […]
Researchers at the University of Trento, the Institut Polytechnique de Paris, and Snap, Inc. have devised an AI system that uses a framework they call Clustering for Action Decomposition and DiscoverY (CADDY) to learn a set of discrete actions from a large library of video clips that can be used to create new “playable” videos […]
Machine learning research is an expensive and energy-hungry business. Training a machine learning model can generate carbon emissions equivalent to building and driving five cars over their lifetimes. But why? Artificial neural networks learn by adjusting weights of parameters and connections until an output matches an answer; for example, an algorithm can play a game […]
Researchers at OpenAI have been able to train a machine learning model fed with pixel sequences to generate coherent images. This is another step toward understanding and bridging the gap between computer vision and language understanding techniques. Google’s BERT, Facebook’s RoBERTa, and OpenAI’s GPT-3 have made great strides with language tasks, but have hitherto been […]