|
|
|
|
|
by chriswarbo
3540 days ago
|
|
It's interesting to think that Schmidhuber's actually applying machine learning methods to the field of machine learning, e.g. see the opening of http://people.idsia.ch/~juergen/deep-learning-conspiracy.htm... If AGI is the goal and machine learning research is the search algorithm, then Schmidhuber's attempting to perform backpropagation by pushing rewards back along the connections :) |
|