English

Scientists demonstrate a new optical neural network training method that can crush electronic microprocessors

100
2023-09-27 15:24:41
See translation

The current deep neural network system (such as ChatGPT) can quickly improve energy efficiency by 100 times in training, and "future improvements will greatly increase by several orders of magnitude. Scientists from MIT and other institutions have demonstrated a new optical neural network training method that can crush state-of-the-art electronic microprocessors.

Moreover, the computational density of the demonstrated system is about two orders of magnitude higher than that of Nvidia, Google, or Graphcore systems.

Basically, this means that the most advanced models can be trained with 100 times less energy and occupy less space at the same speed.

Artificial neural networks mimic the way biological brains process information. These artificial intelligence systems aim to learn, combine, and summarize information from big datasets, reshaping the field of information processing. Current applications include images, objects, speech recognition, games, medicine, and physical chemistry.

The current artificial intelligence model has reached hundreds of billions of artificial neurons, showing exponential growth and posing challenges to current hardware capabilities.

This paper demonstrates that optical neural network (ONN) methods with high clock speed, parallelism, and low loss data transmission can overcome current limitations.

Our technology opens up a path for large-scale optoelectronic processors to accelerate machine learning tasks from data centers to decentralized edge devices, "the paper wrote.

The ONN method is expected to alleviate the bottlenecks of traditional processors, such as the number of transistors, data mobility energy consumption, and semiconductor size. ONN uses light, which can carry a large amount of information simultaneously due to its wide bandwidth and low data transmission loss. In addition, many photonic circuits can be integrated to expand the system.

In order to move light for calculation, the team led by MIT utilized many laser beams, which were described as "using mass-produced micrometer scale vertical cavity surface emitting lasers for neuron coding".

The researchers explained, "Our scheme is similar to the 'axon synapse dendrite' structure in biological neurons
They believe that the demonstrated system can be expanded through mature wafer level manufacturing processes and photon integration.

Dirk Englund, Associate Professor of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology and the head of this work, explained to SciTechDaily that the size of models such as ChatGPT is limited by the capabilities of today's supercomputers. Therefore, training larger models is not economically feasible.

He claimed, "Our new technology can make it possible to cross machine learning models, otherwise it would not be possible in the near future.

This paper titled "Deep Learning Using Coherent VCSEL Neural Networks" was published by a large team of scientists. This work has received support from the Army Research Office, NTT Research, and NTT Netcast Awards, as well as financial support from the Volkswagen Foundation. The three researchers of the team have applied for patents related to this technology.

Source: Laser Network

Related Recommendations
  • Cambridge scientists have achieved the long-sought quantum state stability in new 2D materials

    Scientists at the Cavendish laboratory have discovered the spin coherence of hexagonal boron nitride (hBN) under normal conditions, providing new prospects for the application of quantum technology.Researchers at Cavendish Laboratory have found that a single "atomic defect" in a material called hexagonal boron nitride (hBN) maintains spin coherence at room temperature and can be manipulated using ...

    2024-05-27
    See translation
  • Is CTC technology in the booming new energy industry likely to disrupt the fiber laser industry?

    Recently, the term CTC technology has become a hot topic in the new energy vehicle industry. During the relatively slow period of electrochemical innovation, this structural innovation effectively helped the new energy industry reduce costs and increase efficiency, while also increasing the range of new energy vehicles to a certain extent. However, recently the author learned that the concept of C...

    2023-09-18
    See translation
  • The Ruefeng 30w picosecond laser brings unprecedented possibilities in the art of cutting resin eye lenses

    Ruifeng Picosecond laser: Open the door to the art of cutting resin eye lensesAs an important innovation in the modern eyewear industry, resin lenses bring us visual clarity and comfort with their lightness, transparency and impact resistance.However, with the continuous improvement of people's demand for quality and personalization, how to achieve accurate and beautiful cutting on resin eye lense...

    2023-09-14
    See translation
  • Nuts: Adhere to embrace three-color laser technology, Krypton three-color laser optical machine to solve the speckle phenomenon

    Nuts is once again making waves in the home projection market with the launch of a new home projection product, Nuts N1 Air tri-color laser projector at a historically low price.In the increasingly "volume" home projection market, unswervingly layout of three-color laser nuts, breaking out of their own world.Laser projection permeability increases, nut is on topIn the first half of 2023, the home ...

    2023-09-05
    See translation
  • French researchers develop spiral lenses with optical vortex effects

    As humans stand at the forefront of a new era of space exploration, the National Laboratory of the International Space Station is taking the lead in carrying out a groundbreaking initiative that may completely change the way we understand and utilize space for research and development. In a recent development, Northrop Grumman's 20th commercial supply service mission has become an innovative light...

    2024-02-17
    See translation