Illustration of the on-chip classification process with the Yin-Yang dataset. Each symbol represents the spike time delay for various classifying neurons.
Credit: Göltz and Kriener et al. (Heidelberg / Bern)
RESEARCHERS FROM HEIDELBERG AND BERN DEVELOP A NEW TRAINING APPROACH FOR SPIKING NEURAL NETWORKS
Developing a machine that processes information as efficiently as the human brain has been a long-standing research goal towards true artificial intelligence. An interdisciplinary research team at Heidelberg University and the University of Bern (Switzerland) led by Dr Mihai Petrovici is tackling this problem with the help of biologically-inspired artificial neural networks.
Spiking neural networks, which mimic the structure and function of a natural nervous system, represent promising candidates because they are powerful, fast, and energy-efficient. One key challenge is how to train such complex systems. The German-Swiss research team has now developed and successfully implemented an algorithm that achieves such training.
The nerve cells (or neurons) in the brain transmit information using short electrical pulses known as spikes. These spikes are triggered when a certain stimulus threshold is exceeded. Both the frequency with which a single neuron produces such spikes and the temporal sequence of the individual spikes are critical for the exchange of information. “The main difference of biological spiking networks to artificial neural networks is that, because they are using spike-based information processing, they can solve complex tasks such as image recognition and classification with extreme energy efficiency,” states Julian Göltz, a doctoral candidate in Dr Petrovici’s research group.
Both the human brain and the architecturally similar artificial spiking neural networks can only perform at their full potential if the individual neurons are properly connected to one another. But how can brain-inspired – that is, neuromorphic – systems be adjusted to process spiking input correctly? “This question is fundamental for the development of powerful artificial networks based on biological models,” stresses Laura Kriener, also a member of Dr Petrovici’s research team. Special algorithms are required to guarantee that the neurons in a spiking neural network fire at the correct time. These algorithms adjust the connections between the neurons so that the network can perform the required task, such as classifying images with high precision.
The team under the direction of Dr Petrovici developed just such an algorithm. “Using this approach, we can train spiking neural networks to code and transmit information exclusively in single spikes. They thereby produce the desired results especially quickly and efficiently,” explains Julian Göltz. Moreover, the researchers succeeded in implementing a neural network trained with this algorithm on a physical platform – the BrainScaleS-2 neuromorphic hardware platform developed at Heidelberg University.
According to the researchers, the BrainScaleS system processes information up to a thousand times faster than the human brain and needs far less energy than conventional computer systems. It is part of the European Human Brain Project, which integrates technologies like neuromorphic computing into an open platform called EBRAINS. “However, our work is not only interesting for neuromorphic computing and biologically inspired hardware. It also acknowledges the demand from the scientific community to transfer so-called Deep Learning approaches to neuroscience and thereby further unveil the secrets of the human brain,” emphasises Dr Petrovici.
Original Article: SOLVING COMPLEX LEARNING TASKS IN BRAIN-INSPIRED COMPUTERS
The Latest on: Spiking neural networks
- Renesas tapes out spiking neural network chipon December 5, 2022 at 6:56 am
Renesas is taping out a chip using the spiking neural network (SNN) technology developed by Brainchip. This is part of a move to boost the leading edge performance of its chips for the Internet of ...
- AI uses artificial sleep to learn new task without forgetting the laston November 29, 2022 at 1:49 pm
Artificial intelligence can learn and remember how to do multiple tasks by mimicking the way sleep helps us cement what we learned during waking hours. “There is a huge trend now to bring ideas ...
- Study Finds that Sleep Prevents Catastrophic Forgetting in Spiking Neural Networkson November 28, 2022 at 2:31 pm
A new study published by Maxim Bazhenov Lab at UC San Diego found that replicating sleep in spiking neural networks allows for these ...
- Like a human? Artificial neural networks need to sleep to learn betteron November 25, 2022 at 3:42 am
According to a recent study by the University of California, San Diego, neural networks can imitate the sleep patterns of the human brain in order to tackle catastrophic forgetting. "The brain is very ...
- Neural Networks Learn Better by Mimicking Human Sleep Patternson November 24, 2022 at 7:55 am
San Diego is exploring how artificial neural networks could mimic sleep patterns of the human brain to mitigate the problem of catastrophic forgetting. The research was published in PLOS ...
- UC San Diego: Artificial Neural Networks Learn Better When They Spend Time Not Learning at Allon November 22, 2022 at 4:03 pm
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 ...
- Like Human Brains, Artificial Neural Networks Need Reston November 21, 2022 at 3:04 am
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 ...
- Artificial neural networks learn better when they spend time not learning at allon November 18, 2022 at 2:41 pm
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 ...
- Inducing brain-like sleep in an artificial spiking neural network helps it to keep learning without “catastrophic forgetting”on November 10, 2022 at 11:03 am
Editor's Note: The paper itself will publish later than expected (next Tuesday at 1400/2:00 p.m. ET). The embargo/release will be public at Nov. 10 at 1400/2:00 p.m. ET as planned. Funding: This ...
via Bing News
The Latest on: Spiking neural networks
[google_news title=”” keyword=”spiking neural networks” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News