Wednesday, March 27, 2024

One step closer to light-based, brain-like computing chip

Artificial intelligence has made humans’ life very easy. But, with a more complex application, computers still quickly come up against their own limitations. One of the reasons for this is that a computer traditionally has separate memory and processor units. And the consequences of which is that all the data have to be sent back and forth between the two. When compared to that, the human brain is far ahead of even the most modern computers as it processes and stores information in the same place. Our brain contains a million-billion synapses or connections between neurons.

Well, the journey to creating technology that functions as a brain is still a very long one. An international team of researchers from the Universities of Münster (Germany), Oxford and Exeter (both UK) has now succeeded in developing a piece of hardware which could pave the way for creating computers which resemble the human brain.

The team managed to develop a chip that has a network of artificial neurons that works with light and can imitate the behavior of neurons and their synapses.

Also, the team was able to demonstrate that this optical neurosynaptic network is able to learn from information and use that same information for computing and recognizing patterns. Also, the system produces the data many times faster, as it functions only with light and not with traditional electrons.

This integrated photonic system is an experimental milestone,” says Prof. Wolfram Pernice from Münster University and lead partner in the study. “The approach could be used later in many different fields for evaluating patterns in large quantities of data, for example in medical diagnoses.

For the first time, the scientists succeeded in merging many nanostructured phase-change materials into one neurosynaptic network. Their light-based chip contains four artificial neurons and a total of 60 synapses. The structure of the chip was consists of different layers. It was based on the Wavelength Division multiplex technology, a process in which light is transmitted to different channels in optical nanoscritic.

For testing this brain-like computing chip, the researchers fed the chip with information in the form of light pulses with two different algorithms of machine learning. In this process, the artificial system can learn from examples and finally, generalize them.

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,” added co-author Prof. Harish Bhaskaran from the University of Oxford.

For example, cancer cells can be identified automatically with the help of such hardware. However, before such applications become real, further improvement will be needed. The researchers need to increase the number of artificial neurons and synapses and increase the depth of neural networks.