Brain-Inspired Nanoscale Device to Power an Artificial System

Memristors are resistors that have the ability to remember their prior resistance and can power a neural network as a result. They regulate or limit the flow of electrical current in a circuit. Discovering this is a fantastic breakthrough for the team led by the University of Southampton as these devices could potentially be used to power artificial human brain systems.





The researcher’s memristors were able to learn and relearn different inputs just as a human brain would decipher. Lead author, Dr. Alex Serb from Electronics and Computer Science at the University of Southampton said, “Memristors offer a possible route towards that end by supporting many fundamental features of learning synapses in extremely compact volumes and at exceptionally low energy costs. If artificial brains are ever going to become a reality, therefore, memristive synapses have to succeed.”

The memristor chip
The memristor chip

Because memristors remember previous states, they should also use much less power than traditional batteries. It’s still early days for this type of battery, and hopefully, things can only get better as it’s definitely not at the stage where it could replicate an entire human brain yet. But, that doesn’t mean to say that it’s not helpful in some smaller ways and the Southampton team were keen to point out that not much work is needed for this. By just adding sensors you could classify objects and patterns without any human intervention. This would be particularly helpful in hard to reach or dangerous areas and could potentially save people’s lives.





More News To Read

Comments

comments