AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Transfer Learning - Scaling
More and more training models are either uns vised, or at some level between thats all supervised. The thing that i am curious about here is, how should i think about this in in terms of transfer learning? Is this something that i would use as a base for transfer learning to build upon? Yes, i think that when they're doing their port two things are the two kind of pillars on which foundation models, that they're calling them, are built. If i'm remembering right, they talk about transfer learning and scale.