Artificial neural networks are computing systems inspired by biological neural networks that constitute animal brains. Like biological models, they can learn (be trained) by processing examples and forming probability associations, then apply that information to other tasks.
Depending on age, humans need 7 to 13 hours of sleep per 24 hours. During this time, a lot happens: Heart rate, breathing and metabolism ebb and flow; hormone levels adjust; the body relaxes. Not so much in the brain.
“The brain is very busy when we sleep, repeating what we have learned during the day,” said Maxim Bazhenov, PhD, professor of medicine and a sleep researcher at University of California San Diego School of Medicine. “Sleep helps reorganize memories and presents them in the most efficient way.”
In previous published work, Bazhenov and colleagues have reported how sleep builds rational memory, the ability to remember arbitrary or indirect associations between objects, people or events, and protects against forgetting old memories.
Artificial neural networks leverage the architecture of the human brain to improve numerous technologies and systems, from basic science and medicine to finance and social media. In some ways, they have achieved superhuman performance, such as computational speed, but they fail in one key aspect: When artificial neural networks learn sequentially, new information overwrites previous information, a phenomenon called catastrophic forgetting.
“In contrast, the human brain learns continuously and incorporates new data into existing knowledge,” said Bazhenov, “and it typically learns best when new training is interleaved with periods of sleep for memory consolidation.”
Writing in the November 18, 2022 issue of PLOS Computational Biology, senior author Bazhenov and colleagues discuss how biological models may help mitigate the threat of catastrophic forgetting in artificial neural networks, boosting their utility across a spectrum of research interests.
The scientists used spiking neural networks that artificially mimic natural neural systems: Instead of information being communicated continuously, it is transmitted as discrete events (spikes) at certain time points.
They found that when the spiking networks were trained on a new task, but with occasional off-line periods that mimicked sleep, catastrophic forgetting was mitigated. Like the human brain, said the study authors, “sleep” for the networks allowed them to replay old memories without explicitly using old training data.
“It meant that these networks could learn continuously, like humans or animals. Understanding how human brain processes information during sleep can help to augment memory in human subjects. Augmenting sleep rhythms can lead to better memory. In other projects, we use computer models to develop optimal strategies to apply stimulation during sleep, such as auditory tones, that enhance sleep rhythms and improve learning. This may be particularly important when memory is non-optimal, such as when memory declines in aging or in some conditions like Alzheimer’s disease.”
Maxim Bazhenov, PhD, professor of medicine and a sleep researcher at University of California San Diego School of Medicine.
Memories are represented in the human brain by patterns of synaptic weight — the strength or amplitude of a connection between two neurons.
“When we learn new information,” said Bazhenov, “neurons fire in specific order and this increases synapses between them. During sleep, the spiking patterns learned during our awake state are repeated spontaneously. It’s called reactivation or replay.
“Synaptic plasticity, the capacity to be altered or molded, is still in place during sleep and it can further enhance synaptic weight patterns that represent the memory, helping to prevent forgetting or to enable transfer of knowledge from old to new tasks.”
When Bazhenov and colleagues applied this approach to artificial neural networks, they found that it helped the networks avoid catastrophic forgetting.
“It meant that these networks could learn continuously, like humans or animals. Understanding how human brain processes information during sleep can help to augment memory in human subjects. Augmenting sleep rhythms can lead to better memory.
“In other projects, we use computer models to develop optimal strategies to apply stimulation during sleep, such as auditory tones, that enhance sleep rhythms and improve learning. This may be particularly important when memory is non-optimal, such as when memory declines in aging or in some conditions like Alzheimer’s disease.”
Original Article: Artificial Neural Networks Learn Better When They Spend Time Not Learning at All
More from: University of California San Diego School of Medicine | University of California San Diego | Czech Academy of Sciences
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Artificial neural networks
- Multiplexed neuron sets make smaller optical neural networks possible
Seeking to improve the practicality of optical neural networks that use wavelength division multiplexing, a research team developed a structure called multiplexed neuron sets and a corresponding ...
- AI/ML Innovations Inc. Introduces its Proprietary "Long ECG Neural Network"
Highlights: 100 million+ ECGs are performed annually in the USA. AIML's proprietary "Long ECG Neural Net" reduces labeling of long ECGs from several days to under 5 minutes. Provides unsurpassed ...
- Study finds AI improves efficiency of artificial pancreas system for Type 1 diabetics
UVA researchers compared an advanced experimental artificial pancreas system with an artificial pancreas algorithm incorporating AI.
- Adding AI to artificial pancreas enhances efficiency, study finds
Adding advanced artificial intelligence to an artificial pancreas regulating type 1 diabetes is safe and improves the system's efficiency, a first-of-its-kind study from the University of Virginia ...
- Artificial intelligence enhances monitoring of threatened marbled murrelet
Artificial intelligence analysis of data gathered by acoustic recording devices is a promising new tool for monitoring the marbled murrelet and other secretive, hard-to-study species, research by ...
Go deeper with Bing News on:
Artificial neural networks continuous learning
- Training AI to Master the World of Pokémon [Video]
A YouTube video by Peter Whidden showcases an intriguing project where AI is trained to play Pokémon with a surprising level of ...
- Innovative data integration in 2024: Pioneering the future of data integration
This article discusses the latest advancements in the data integration industry and how organisations can successfully integrate these technologies into their existing data strategy.
- Workers with these AI skills are getting cash premiums
As AI deployments become more critical to digital transformation projects, organizations are struggling to find skilled workers to support the new technology, so they're paying premiums for ...
- AI’s Inner Dialogue: How Self-Reflection Enhances Chatbots and Virtual Assistants
Explore how self-reflection enhances AI chatbots and virtual assistants improving response accuracy, reducing bias, and fostering inclusivity ...
- AI Efficiency Breakthrough: How Sound Waves Are Revolutionizing Optical Neural Networks
Researchers have developed a way to use sound waves in optical neural networks, enhancing their ability to process data with high speed and energy efficiency. Optical neural networks may provide the ...