How do you go from self-play to the real world? : Transfer learning
NeurIPS 2017 Meta Learning Symposium: https://lnkd.in/e7MdpPc
"I think transfer learning is the key to general intelligence. And I think the key to doing transfer learning will be the acquisition of conceptual knowledge that is abstracted away from perceptual details of where you learned it from." — Demis Hassabis
#artificialintelligence #deeplearning #metalearning #reinforcementlearning #selfplay
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN
NeurIPS 2017 Meta Learning Symposium: https://lnkd.in/e7MdpPc
"I think transfer learning is the key to general intelligence. And I think the key to doing transfer learning will be the acquisition of conceptual knowledge that is abstracted away from perceptual details of where you learned it from." — Demis Hassabis
#artificialintelligence #deeplearning #metalearning #reinforcementlearning #selfplay
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN
Meta-Learning with Implicit Gradients
Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine : https://lnkd.in/g9H6mZ2
#MachineLearning #ArtificialIntelligence #Optimization #Control #MetaLearning
Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine : https://lnkd.in/g9H6mZ2
#MachineLearning #ArtificialIntelligence #Optimization #Control #MetaLearning
arXiv.org
Meta-Learning with Implicit Gradients
A core capability of intelligent systems is the ability to quickly learn new
tasks by drawing on prior experience. Gradient (or optimization) based
meta-learning has recently emerged as an...
tasks by drawing on prior experience. Gradient (or optimization) based
meta-learning has recently emerged as an...