AI specialist Jürgen Schmidhuber on inductive inference, universal Solomonoff prior and measuring probability of different events.
Read the full text on our website:
‘Using Bayes’ rule we can say: okay, let’s look at the possible futures Y, so the entire life will be the combination of X and Y, and now the question is, what is the most likely Y that we can observe given the X that we already have seen? ‘
Jürgen Schmidhuber, Scientific Director, Swiss AI Lab IDSIA
Artificial Consciousness:
Gödel Machine:
This lecture is part of the collaboration between Serious Science and the Technology Contests Up Great READ//ABLE:
Be the first to find out about our new videos and articles. Learn interesting facts about various topics and people. Discover the answers to the big questions. Be in the know.
Follow us:
We are on Patreon:
Facebook —
Twitter —
YouTube —
Instagram —
Tumblr —
VK —
This seems to be related to the "P vs. NP" problem.
thank you
Should time be factored in? As ai lifetimes vary greatly take fruitfly vs. Human. With each different life span and their previous exposures how can the future be predicted. A meal for me is a pleasurable experience. In a 3rd world country a meal can completely change a life. End or extend due to quality ect…for me? Not so much. People vary so vastly isn't it improbable?
very interesting! ^_^