Neuromorphic computer: Researchers have discovered hardware that mimics the behavior of the human brain –

Certainly, technological advances in artificial intelligence (AI) are bringing ultra-fast computing closer, thanks to the neuromorphic computer. The question, however, is whether the current infrastructure can handle this workload.

In reality, the codes people write often run on traditional silicon architectures. The latter, however are not suitable for this task. Researchers from Purdue University, the University of California at San Diego (USCD) and the École Supérieure de Physique et de Chimie Industrielles (ESPCI) in Paris then tried to solve this challenge. They published their findings in Advanced Electronic Materials, where they explored an approach to reshape hardware by mimicking synapses in the human brain.

A promising future for neuromorphic computing

The neuromorphic computer, which imitates the behavior of the brain, is based on special computer chips. In the brain, neurons transmit information across synapses, which play a key role in memory. Researchers have found that vanadium oxides are promising for neuromorphic computing because they enable the creation of both artificial neurons and synapses.

The architecture of neuromorphic computers has one major advantage: lower energy consumption than traditional silicon architectures. That’s up to them Ability to mimic the basic components of a brain, namely neurons and synapses. Unlike silicon, which is suitable for memory storage, neuromorphic materials mimic neuronal behavior.

However, finding suitable materials to create both good synapses and good artificial neurons is a challenge. Only a few quantum materials are promising in this area, especially vanadium dioxide. The researchers found that memory accumulates throughout the vanadium sample. This discovery then opens up new possibilities for controlling this property.

The results of this research have been revealed. However, microscopic videos have shown that changes in the metallic and insulating domains of vanadium cause a Memory accumulation in the entire sample.

This memory is created by local temperature changes as the material transitions from insulator to metal and vice versa. There preferential diffusion of point defects in metallic domains seems to contribute to this accumulation of memories.

The researchers now want to continue their work by locally modifying the vanadium and observing the effects. In particular, the effects of ion bombardment on the surface of the material.

This could make it possibleimprove the synaptic behavior of this neuromorphic material. This is done by directing the electrical current to the areas where the memory effect is most pronounced.