At A Glance – Neuromorphic Hardware

Computer components inspired by the human brain

Neuromorphic hardware is any electronic device which mimics the natural biological structures of our nervous system. As we increasingly want computers to perform complicated tasks for us, neuromorphic hardware is being pursued as a way of replicating our cognitive abilities in machines. Our brains process information faster and more efficiently than computers, largely due to the architecture of their neural systems. Mapping this architecture onto machines is an obvious way of giving them human like processing abilities. However, traditional computers operate very differently to our brains, making this a difficult feat.

Scientists at IBM have created TrueNorth, a neuromorphic computer chip which contains the largest number of transistors of any IBM chip to date. This powerful chip breaks away from the traditional computer architectures of the past to create processing power inspired by the brain. In the future, IBM researchers hope to combine the capabilities of traditional computer chips with neuromorphic chips such as TrueNorth, to create a holistic computing intelligence.

A key part of neuromorphic engineering is understanding how our neurons process signals and compute information, so that this can be applied to electronic components. In order to gain insight into electrical circuits and biological processes, neuromorphic engineers require interdisciplinary knowledge of biology, physics, maths, computer science and electronic engineering. The field not only gives us greater understanding of computers and electrical components, but also advances our knowledge of the brain.

For more insights into technology’s most interesting terms, sign up to our free weekly newsletter.