Data from: Neural modularity helps organisms evolve to learn new skills without forgetting old

Kai Olav Ellefsen, Jean-Baptiste Mouret & Jeff Clune
A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks...
1 citation reported since publication in 2016.
810 views reported since publication in 2016.

These counts follow the COUNTER Code of Practice, meaning that Internet robots and repeats within a certain time frame are excluded.
What does this mean?
129 downloads reported since publication in 2016.

These counts follow the COUNTER Code of Practice, meaning that Internet robots and repeats within a certain time frame are excluded.
What does this mean?