Scenes from a memory: neural audio/video generation
Generating representations is the ultimate act of creativity. Recent advancements in neural networks (and in processing power) brought us the capability to perform regression against complex samples like images and audio. In this presentation we show the underlying mechanics of media generation from latent space representation of abstract visual ideas, real embodiment of “Platonic” concepts, with Variational Autoencoders, Generative Adversarial Networks, neural style transfer and PixelRNN/CNN along with current practical applications like DeepFake.
Computer engineer with 11 years of experience, specialized in mission critical, high traffic, high available Linux architectures and infrastructures (before the cloud was out), with a relevant experience in development and management of web services. He has served as Infrastructure Lead in 4 companies (Translated, N26, Wanderio, Klar) and participated in 2 EU multimillion funded NLP research projects (MateCAT, ModernMT). Alberto has a variegated bundle of experience, that ranges from devops to machine learning, from the corporate banking to the mutable startup world.