Scimex: Animals, including humans, have brains that include separate areas for
memorising different things - like language and facial recognition - and
as such, can't just overwrite previous knowledge when learning a new
skill. Now, international scientists have found that when they apply
this brain model to computers it helps them to avoid 'catastrophic
forgetting' and not wipe out lots of information when saving new
information.
New research suggests that when brains are organized into modules
they are better at learning new information without forgetting old
knowledge. The findings—published this week in PLOS Computational
Biology—not only shed light on the evolution of intelligence in natural
animals, but will also accelerate attempts to create artificial
intelligence (AI).
Kai Olav Ellefsen (Norwegian University of
Science and Technology), Jean-Baptiste Mouret (Pierre & Marie Curie
University) and Jeff Clune (University of Wyoming) used simulations of
evolving computational brain models called artificial neural networks to
show that more modular brains learn more and forget less.
The
brains of animals (including humans) are modular, which means they have
many separate units, such as those for language and facial recognition.
While natural animals tend to forget gradually, artificial neural
networks currently exhibit what is called 'catastrophic forgetting'.
They rapidly overwrite previously acquired knowledge when learning a new
skill. The researchers found that modularity significantly reduced such
catastrophic forgetting in these computer brains.
In future work, the researchers plan to dramatically scale up the
complexity of the brain models and the difficulty of the tasks they ask
the neural networks to learn. "Building models that incorporate both
evolution and learning is critical to understanding the evolution of the
animal nervous system", Jean-Baptiste Mouret says. Jeff Clune adds:
"The ultimate goal of artificial intelligence research is to produce AI
that can learn many different skills and get better at each of them over
time, just as humans and animals do. We must solve the problem of
catastrophic forgetting to realize that goal. This work is an important
step in that direction, but it is just one step in a long journey."