A Step Towards Light-Based, Brain-Like Computing Chip

Schematic illustration of a light-based, brain-inspired chip. By mimicking biological neuronal systems, photonic neuromorphic processors provide a promising platform to tackle challenges in machine learning and pattern recognition. (Source: J. Feldmann)

An inter­national team of researchers from the Univer­sities of Münster (Germany), Oxford and Exeter (both UK) have now succeeded in developing a piece of hardware which could pave the way for creating computers which resemble the human brain. The scientists managed to produce a chip containing a network of arti­ficial neurons that works with light and can imitate the behaviour of neurons and their synapses.

The researchers were able to demonstrate, that such an optical neurosynaptic network is able to learn infor­mation and use this as a basis for computing and recog­nizing patterns – just as a brain can. As the system functions solely with light and not with traditional electrons, it can process data many times faster. “This inte­grated photonic system is an experimental milestone,” says Wolfram Pernice. “The approach could be used later in many different fields for evaluating patterns in large quan­tities of data, for example in medical diagnoses.”

Most of the existing approaches relating to neuro­morphic networks are based on electronics, whereas optical systems – in which photons are used – are still in their infancy. The principle which the German and British scientists have now presented works as follows: optical waveguides that can transmit light and can be fabri­cated into optical microchips are integrated with phase-change materials – which are already found today on storage media such as re-writable DVDs. These phase-change materials are characterised by the fact that they change their optical properties drama­tically, depending on whether they are crystalline – when their atoms arrange themselves in a regular fashion – or amorphous – when their atoms organise themselves in an irregular fashion. This phase-change can be triggered by light if a laser heats the material up. “Because the material reacts so strongly, and changes its properties drama­tically, it is highly suitable for imitating synapses and the transfer of impulses between two neurons,” says Johannes Feldmann, who carried out many of the experiments as part of his PhD thesis at the Münster University.

Now, the scientists succeeded for the first time in merging many nano­structured phase-change materials into one neuro­synaptic network. The researchers developed a chip with four artificial neurons and a total of 60 synapses. The structure of the chip – consisting of different layers – was based on the wavelength division multiplex tech­nology, which is a process in which light is trans­mitted on different channels within the optical nanocircuit. In order to test the extent to which the system is able to recognise patterns, the researchers fed it with information in the form of light pulses, using two different algorithms of machine learning. In this process, an artificial system learns from examples and can, ultimately, generalise them. In the case of the two algorithms used – both in supervised and in unsupervised learning – the artificial network was ulti­mately able, on the basis of given light patterns, to recognise a pattern being sought – one of which was four consecutive letters.

“Our system has enabled us to take an important step towards creating computer hardware which behaves similarly to neurons and synapses in the brain and which is also able to work on real-world tasks,” says Wolfram Pernice. “By working with photons instead of electrons we can exploit to the full the known potential of optical tech­nologies – not only in order to transfer data, as has been the case so far, but also in order to process and store them in one place,” adds Harish Bhaskaran from the Uni­versity of Oxford.

A very specific example is that with the aid of such hardware cancer cells could be identified automa­tically. Further work will need to be done, however, before such appli­cations become reality. The researchers need to increase the number of artificial neurons and synapses and increase the depth of neural networks. This can be done, for example, with optical chips manu­factured using silicon tech­nology. “This step is to be taken in the EU joint project Fun-COMP by using foundry processing for the pro­duction of nanochips,” says co-author and leader of the Fun-COMP project, David Wright from the University of Exeter. (Source: U. Muenster)

Reference: J. Feldmann et al.: All-optical spiking neurosynaptic networks with self-learning capabilities, Nature 569, 208 (2019); DOI: 10.1038/s41586-019-1157-8

Link: Responsive Nanosystems (W. Pernice), University of Muenster, Germany

Speak Your Mind

*