Generative Curiosity Unleashed
Jürgen discusses the evolution of generative adversarial networks, coining the term "artificial curiosity" to describe their potential in robotic exploration. He reflects on the pivotal moment in 2009 when advancements in computing power allowed his LSTM models to excel in competitions. The conversation also touches on the "hardware lottery," highlighting how the gaming industry's need for matrix multiplications inadvertently propelled deep learning forward.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Jurgen Schmidhuber on Humans co-existing with AIs
Related Questions