Google Scientists Generate Realistic Videos at Scale with AI

Google research scientists report that they have produced realistic frames from open source video data sets at scale. Neural networks are able to generate complete videos from only a start and end frame, but it’s the complexity, information density and randomness of video that have made it too challenging to create such realistic clips at scale. The scientists wrote that, to their knowledge, “this is the first promising application of video-generation models to videos of this complexity.” The systems are based on a neural architecture known as Transformers, as described in a Google Brain paper, and are autoregressive, “meaning they generate videos pixel by pixel.” Continue reading Google Scientists Generate Realistic Videos at Scale with AI

IBM’s SyNAPSE Chip Mimics the Workings of a Human Brain

IBM recently unveiled the second generation of a new type of computer chip that consumes less power and performs faster than traditional chips based on Von Neumann architecture. The SyNAPSE chip, which is still in development, was designed to function like the human brain, using more than a million “neurons” communicating through electrical spikes. This new technology requires a new type of programming language as well, but the performance gains are massive. Continue reading IBM’s SyNAPSE Chip Mimics the Workings of a Human Brain