Computation is fixed in a rut. The integrated circuits that powered the past 50 years of technological revolution are reaching their limits.
This problematic situation has computer scientists struggling for new ideas: new devices built using novel physics, new ideas of organizing parts within computers and even algorithms that use new or existing systems efficiently. To help coordinate new ideas, Sandia National Laboratories has assisted organizing the( Institute of Electrical and Electronics Engineers) IEEE International Conference on Rebooting Computing held.
Researchers from Sandia's Data-driven and Neural Computing Dept. will present three papers at the conference, highlighting the breadth of potential non-conventional neural computing applications.
"We're taking an effort at the scope of what neural algorithms can do. We're not trying to be exhaustive, but rather we're trying to highlight the kind of application over which algorithms may be impressive," said Brad Aimone, a computational neuroscientist and co-author of one paper. Historically, neural computing has been seen as approximate and selective, he added; however, Sandia researchers in their papers aim to extend neural algorithms so they incorporate severity and predictability, which shows they may have a role in high performance scientific computing.
Troubles and benefits of continuously learning
The brain is continually learning. "While we do learn in school, our learning doesn't stop when school ends. Instead, our brains are continually familiarizing through processes, such as synaptic modifications. However, most machine-learning algorithms learn once and are done," said Vineyard, a computer scientist.
Most commonly named machine-learning algorithms have a learning phase and an individual testing and operation phase. This is really time consuming task. Determined—and challenging—attempts to develop algorithms that learn continuously also run the risk of the algorithm "learning" something that's wrong, Vineyard said.
What are dynamical systems anyway?
A dynamical system is a calculation that describes how things change with time. A simple dynamical system is a function that describes the movement of a grandfather clock's pendulum. "The idea behind using dynamical systems for computation is to deevelop a machine such that its dynamics—which has to do with the structure of the machine—will lead it to the answer based on supplement it the question," said Rothganger, a computer scientist.
Both our brains and, in a way, traditional computers are dynamical systems: They find answers just based on the question and how the computers are made, said Rothganger. His paper proposes that if researchers think of a traditional scientific computing problem, as a dynamical system, they could solve them rigorously on neuro-inspired systems.