Intelligent machines of the future may need to sleep as much as we do.
States that resemble sleep-like cycles in simulated neural networks quell the instability that comes with uninterrupted self-learning in artificial analogs of brains
No one can say whether androids will dream of electric sheep, but they will almost certainly need periods of rest that offer benefits similar to those that sleep provides to living brains, according to new research from Los Alamos National Laboratory.
“We study spiking neural networks, which are systems that learn much as living brains do,” said Los Alamos National Laboratory computer scientist Yijing Watkins. “We were fascinated by the prospect of training a neuromorphic processor in a manner analogous to how humans and other biological systems learn from their environment during childhood development.”
It was as though we were giving the neural networks the equivalent of a good night’s rest
Watkins and her research team found that the network simulations became unstable after continuous periods of unsupervised learning. When they exposed the networks to states that are analogous to the waves that living brains experience during sleep, stability was restored. “It was as though we were giving the neural networks the equivalent of a good night’s rest,” said Watkins.
The discovery came about as the research team worked to develop neural networks that closely approximate how humans and other biological systems learn to see. The group initially struggled with stabilizing simulated neural networks undergoing unsupervised dictionary training, which involves classifying objects without having prior examples to compare them to.
“The issue of how to keep learning systems from becoming unstable really only arises when attempting to utilize biologically realistic, spiking neuromorphic processors or when trying to understand biology itself,” said Los Alamos computer scientist and study coauthor Garrett Kenyon. “The vast majority of machine learning, deep learning, and AI researchers never encounter this issue because in the very artificial systems they study they have the luxury of performing global mathematical operations that have the effect of regulating the overall dynamical gain of the system.”
The researchers characterize the decision to expose the networks to an artificial analog of sleep as nearly a last ditch effort to stabilize them. They experimented with various types of noise, roughly comparable to the static you might encounter between stations while tuning a radio. The best results came when they used waves of so-called Gaussian noise, which includes a wide range of frequencies and amplitudes. They hypothesize that the noise mimics the input received by biological neurons during slow-wave sleep. The results suggest that slow-wave sleep may act, in part, to ensure that cortical neurons maintain their stability and do not hallucinate.
The groups’ next goal is to implement their algorithm on Intel’s Loihi neuromorphic chip. They hope allowing Loihi to sleep from time to time will enable it to stably process information from a silicon retina camera in real time. If the findings confirm the need for sleep in artificial brains, we can probably expect the same to be true of androids and other intelligent machines that may come about in the future.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- Self-Learning Neuromorphic Chip Market to Potentially Generate Higher Valuation Post COVID 19 Pandemic | Forecast By 2023on June 19, 2020 at 7:32 am
The given Market Research Future's latest report on the global self-learning neuromorphic chip market 2020 is an excellent research ...
- Artificial Brains Need Sleep Too – Desperate AI Researchers Discover Way to Stabilize Neuromorphic Processorson June 16, 2020 at 2:18 am
States that resemble sleep-like cycles in simulated neural networks quell the instability that comes with uninterrupted self-learning in artificial analogs of ...
- BrainChip Launches the Akida Early Access Programon June 15, 2020 at 10:38 am
BrainChip Holdings Ltd announced an Early Access Program (EAP) for the Akida neural processor System-on-Chip (SoC).
- BrainChip Successfully Launches the Akida Early Access Programon June 14, 2020 at 4:22 pm
BrainChip Holdings Ltd (ASX: BRN), a leading provider of Ultra-Low Power, high performance AI technology, today announced an Early Access Program (EAP) for the Akida™ neural processor System-on-Chip ...
- Here’s why artificial brains may need sleep for proper functioningon June 14, 2020 at 2:57 am
The discovery came about as the research team worked to develop neural networks that closely approximate how humans and other biological systems learn to see.
Go deeper with Google Headlines on:
Go deeper with Bing News on:
- In a Hybrid Neural Circuit, Artificial and Biological Neurons Used Dopamine to Communicateon June 23, 2020 at 7:00 am
By playing with how much dopamine accumulates at the artificial neuron, the team found that they loosely mimic a learning rule called spike learning.
- Apple gives Macs a brain transplant with new Arm chips starting this yearon June 22, 2020 at 8:43 pm
Apple is overhauling its Mac computers with its own Arm chips, close cousins to those it designs for its own iPhones and iPads. Moving away from the Intel processors it's used for the last 14 years is ...
- NeuroMem: Analog Graphene-Based Resistive Memory for Artificial Neural Networkson June 22, 2020 at 12:20 pm
Artificial Intelligence (AI) at the edge has become a hot subject of the recent technology-minded publications. The challenges related to IoT nodes gave rise to research on efficient hardware-based ...
- Why aren't people smarter? The dubious benefits of intelligence, real or artificialon June 22, 2020 at 8:07 am
Intelligence -- real or artificial -- is supposed to be a big advantage. But we've had millions of years to evolve real intelligence and dumbness is rampant. Which raises the question: If intelligence ...
- Alex Zanardi 'condition stable' but fears of brain damageon June 20, 2020 at 12:22 pm
Alex Zanardi, the former Formula One driver who became an inspirational Paralympic champion after having both his legs amputated in a motor racing accident almost two decades ago, was fighting for his ...