Summary: A chat with AI stalwart Yoshua Bengio on the origins of generative models
January 3, 2023
The history of generative AI can be traced back to the advent of GANs in 2014. GANs allowed neural networks to generate new images that were convincing enough to be mistaken for real. In 2015, diffusion models were introduced which improved upon the quality of images generated by GANs. Last year, latent diffusion models were introduced which significantly reduced the generation time and cost for images. Probabilistic machine learning is a mix between various subject areas that can help machines understand what learning is through experiences.
Related articles
What Excites Yoshua Bengio about the Future of Generative AI
GANs gave deep learning models something they didn’t have before – imagination
Read the complete article at: analyticsindiamag.com
About The Author
