
Sander Bohte
Photo by Inge Hoogland
Thanks to a mathematical breakthrough, AI applications like speech recognition, gesture recognition and ECG classification can become a hundred to a thousand times more energy efficient. This means it will be possible to put much more elaborate AI in chips, enabling applications to run on a smartphone or smartwatch where before this was done in the cloud.
Running the AI on local devices makes the applications more robust and privacy-friendly: robust, because a network connection with the cloud is no longer necessary. And more privacy friendly because data can be stored and processed locally.
The mathematical breakthrough has been achieved by researchers of Centrum Wiskunde & Informatica (CWI), the Dutch national research center for mathematics and computer science together with the IMEC/Holst Research Centre from Eindhoven. The results have been published in a paper (by Bojian Yin, Federico Corradi, and Sander M. Bohté) of the International Conference on Neuromorphic Systems. The underlying mathematical algorithms have been made available open source.
Under supervision of CWI researcher and UvA professor cognitive neurobiology Sander Bohté, researchers developed a learning algorithm for so-called spiking neural networks. Such networks have been around for some time, but are very difficult to handle from a mathematical perspective, making it hard to put them into practice so far. The new algorithm is groundbreaking in two ways: the neurons in the network are required to communicate a lot less frequently, and each individual neuron has to execute fewer calculations.
“The combination of these two breakthroughs make AI algorithms a thousand times more energy efficient in comparison with standard neural networks, and a factor hundred more energy efficient than current state-of-the-art neural networks”, says principal investigator Sander Bohté.
Inspired by the human brain
Bohté’s inspiration and motivation comes from the incredibly energy efficient way that the human brain processes information (20 Watt). Computers that mimic the brain’s neuronal networks have produced wonderful applications in recent years – ranging from image recognition, speech recognition, automatic translation, to medical diagnoses – but require up to a million times more energy than the human brain.
The spiking neural networks developed by Bohté and his research team differ from those already integrated in AI applications. “The communication between neurons in classical neural networks is continuous and easy to handle from a mathematical perspective. Spiking neurons look more like the human brain and communicate only sparingly and with short pulses. This however means that the signals are discontinuous and much more difficult to handle mathematically.”
New type of computer chip
To run spiking neural networks efficiently in the real-world, a new type of chips are needed. Bohté says that prototypes are already being developed. “All kinds of companies are working hard to make this happen, like our project partner IMEC/Holst Centre.”
Bohté’s methods can train spiking neural networks comprised of up to a few thousand neurons, less than typical classical neural networks, but sufficient for many applications like speech recognition, ECG classification and the recognition of gestures. The next challenge will therefore be to scale up these networks to 100.000 or a million neurons, which will expand the application possibilities even further.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Spiking neural networks
- Scientists integrate two-dimensional materials into silicon microchips for advanced data storage and computation
Two-dimensional materials are expected to revolutionize the semiconductor industry. However, despite multiple studies that have reported prototype devices with promising properties for sensing and ...
- Exploring the neural mechanisms behind how social networks shape our decisions
Over the past decade or so, social scientists have been trying to understand how social networks can influence people's beliefs and behavior. Despite the many studies on this topic, currently very ...
- Neural network IP Listing
WhisPro is a neural network based speech recognition software package, allowing customers to add voice activation to voice-enabled IoT devices. WhisPro™ is targeting the rapidly growing use ... IMG ...
- Combining AI and neuroscience to detect and predict neurological disorders
Study: Convergence of Artificial Intelligence and Neuroscience towards the Diagnosis of Neurological Disorders—A Scoping Review. Image Credit: Maxim Gaigul / Shutterstock.com Neuroscience principles ...
- UC Santa Cruz researcher champions AI language generator SpikeGPT
UC Santa Cruz Assistant Professor of Electrical and Computer Engineering Jason Eshraghian and two undergraduate students have devised a more energy efficient way for AI to process language called ...
Go deeper with Google Headlines on:
Spiking neural networks
[google_news title=”” keyword=”spiking neural networks” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Neural networks
- Vector Databases Emerge to Fill Critical Role in AI
Vector databases arrived on the scene a few years ago to help power a new breed of search engines that are based on neural networks as opposed to keywords. Companies like Home Depot dramatically ...
- Exploring the neural mechanisms behind how social networks shape our decisions
Over the past decade or so, social scientists have been trying to understand how social networks can influence people's beliefs and behavior. Despite the many studies on this topic, currently very ...
- Predictive network technology promises to find and fix problems faster.
As AI and ML are backed by more powerful neural networks, prescriptive analytics will recommend paths to better future outcomes.
- Rock, Paper, Neural Net
This is a neural network, and you need to train a neural network, so where did [Paul] get all that data? roshambo.me offers thousands of paper rock scissor games, and trained the network on more ...
- Neural Network Market | Insights and Opportunities for 2023-2027
Mar 26, 2023 (The Expresswire) -- "Final Report will add the analysis of the impact of COVID-19 on this industry." Latest “Neural Network Market” ...
Go deeper with Google Headlines on:
Neural networks
[google_news title=”” keyword=”neural networks” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]