Uploaded November 2020 | Updated September 2026, 2 weeks ago
AI specialist Jürgen Schmidhuber on credit assignment, recurrent neural networks and how can you solve the parity problem with a network of only five connections.
Read the full text on our website: serious-science.org/deep-learning-10364
'The learning, or the credit assignment, is about finding weights that make the neural network exhibit some desired behavior, such as controlling a robot. Depending on the problem and on how the units are connected, such behavior may require long causal chains of computational stages where each stage is setting the stage for the next processing step, where each stage transforms, often in a non-linear way, the aggregate activation of the entire network. '
Jürgen Schmidhuber, Scientific Director, Swiss AI Lab IDSIA
Neural Networks: serious-science.org/neural-networks-9479
Computer Vision: serious-science.org/computer-vision-8732
This lecture is part of the collaboration between Serious Science and the Technology Contests Up Great READ//ABLE: https://en.ai.upgreat.one/
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.
serious-science.org
Follow us:
We are on Patreon: patreon.com/SeriousScience
Facebook — facebook.com/serious.science.org
Twitter — twitter.com/scienceserious
YouTube — youtube.com/user/SeriousScience
Instagram — instagram.com/serious.science
Tumblr — serious-science.tumblr.com
VK — vk.com/seriousscience
AI specialist Jürgen Schmidhuber on credit assignment, recurrent neural networks and how can you solve the parity problem with a network of only five connections.
Read the full text on our website: serious-science.org/deep-learning-10364
'The learning, or the credit assignment, is about finding weights that make the neural network exhibit some desired behavior, such as controlling a robot. Depending on the problem and on how the units are connected, such behavior may require long causal chains of computational stages where each stage is setting the stage for the next processing step, where each stage transforms, often in a non-linear way, the aggregate activation of the entire network. '
Jürgen Schmidhuber, Scientific Director, Swiss AI Lab IDSIA
Neural Networks: serious-science.org/neural-networks-9479
Computer Vision: serious-science.org/computer-vision-8732
This lecture is part of the collaboration between Serious Science and the Technology Contests Up Great READ//ABLE: https://en.ai.upgreat.one/
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.
serious-science.org
Follow us:
We are on Patreon: patreon.com/SeriousScience
Facebook — facebook.com/serious.science.org
Twitter — twitter.com/scienceserious
YouTube — youtube.com/user/SeriousScience
Instagram — instagram.com/serious.science
Tumblr — serious-science.tumblr.com
VK — vk.com/seriousscience
