Deep learning from a dynamical viewpoint

NUS mathematicians have developed a new theoretical framework based on dynamical systems to understand when and how a deep neural network can learn arbitrary relationships.

Neural stem cells control their own fate

To date, it has been assumed that the differentiation of stem cells depends on the environment they are embedded in. A research group at the University of Basel now describes for the first time a mechanism by which hippocampal ...

page 1 from 2