Learning and remembering “on the fly” with a new nanowire “brain” network

Electrodes interact with the nanowire neural network at the heart of the chip.

Learning and remembering “on the fly” with a new nanowire “brain” network

Critical step passed for developing ‘agile’ and low-energy machine intelligence

Like a collection of ‘Pick Up Sticks’, the self-arranged network of nanowires mimics the synapse function of the brain. In this experiment, a network was trained to access dynamic online data that it learnt and memorised.

For the first time, a physical neural network has successfully been shown to learn and remember ‘on the fly’, in a way inspired by and similar to how the brain’s neurons work.

The result opens a pathway for developing efficient and low-energy machine intelligence for more complex, real-world learning and memory tasks.

Published today in Nature Communications, the research is a collaboration between scientists at the University of Sydney and University of California at Los Angeles.

Lead author Ruomin Zhu, a PhD student from the University of Sydney Nano Institute and School of Physics, said: “The findings demonstrate how brain-inspired learning and memory functions using nanowire networks can be harnessed to process dynamic, streaming data.”

Nanowire networks are made up of tiny wires that are just billionths of a metre in diameter. The wires arrange themselves into patterns reminiscent of the children’s game ‘Pick Up Sticks’, mimicking neural networks, like those in our brains. These networks can be used to perform specific information processing tasks.

Memory and learning tasks are achieved using simple algorithms that respond to changes in electronic resistance at junctions where the nanowires overlap. Known as ‘resistive memory switching’, this function is created when electrical inputs encounter changes in conductivity, similar to what happens with synapses in our brain.

In this study, researchers used the network to recognise and remember sequences of electrical pulses corresponding to images, inspired by the way the human brain processes information.

Supervising researcher Professor Zdenka Kuncic said the memory task was similar to remembering a phone number. The network was also used to perform a benchmark image recognition task, accessing images in the MNIST database of handwritten digits, a collection of 70,000 small greyscale images used in machine learning.

“Our previous research established the ability of nanowire networks to remember simple tasks. This work has extended these findings by showing tasks can be performed using dynamic data accessed online,” she said.

“This is a significant step forward as achieving an online learning capability is challenging when dealing with large amounts of data that can be continuously changing. A standard approach would be to store data in memory and then train a machine learning model using that stored information. But this would chew up too much energy for widespread application.

“Our novel approach allows the nanowire neural network to learn and remember ‘on the fly’, sample by sample, extracting data online, thus avoiding heavy memory and energy usage.”

Mr Zhu said there were other advantages when processing information online.

See Also

“If the data is being streamed continuously, such as it would be from a sensor for instance, machine learning that relied on artificial neural networks would need to have the ability to adapt in real-time, which they are currently not optimised for,” he said.

In this study, the nanowire neural network displayed a benchmark machine learning capability, scoring 93.4 percent in correctly identifying test images. The memory task involved recalling sequences of up to eight digits. For both tasks, data was streamed into the network to demonstrate its capacity for online learning and to show how memory enhances that learning.

Original Article: Nanowire ‘brain’ network learns and remembers ‘on the fly’

More from: University of Sydney | University of California Los Angeles

 

 

The Latest Updates from Bing News

Go deeper with Bing News on:
Nanowire neural network
Go deeper with Bing News on:
Nanowire networks
  • Mobile Networks in the UK 2024

    What is a mobile network? A mobile network is the infrastructure that enables your phone and other mobile devices, such as tablets, to connect with each other and to the internet. The network is ...

  • Social Networking

    The term "social network" refers both to a person's connections to other people in the real world and to a platform that supports online communication, such as Instagram, Facebook, or Twitter.

  • The best mobile networks in 2024, based on our annual customer survey and full reviews

    Here are the UK’s best mobile networks based on our annual survey, Ofcom’s customer service report and RootMetrics’ performance tests Choosing between the best mobile networks isn’t easy.

  • A Beginner's Guide to Content Delivery Networks (CDNs)

    Terms may apply to offers listed on this page. A content delivery network (CDN) is an integral part of website building and management. Here’s what it entails and how best to use one.

  • A Small Business Guide to Creating Network Diagrams

    Terms may apply to offers listed on this page. Network diagrams document critical information about your enterprise network's hardware, security, and configuration. Learn how to create network ...

What's Your Reaction?
Don't Like it!
0
I Like it!
0
Scroll To Top