Neuromorphic computing in Next Gen IT systems

Document Type : Original Article

Author

Department of Mathematics and Computer Science, Iran University of Science and Technology

10.5281/zenodo.15510929
Abstract
Neuromorphic is by no means a new concept. Like many other emerging technologies that are now gaining momentum, neuromorphic has been quietly developing for a long time, but it still needs more work to shine. Neuromorphic systems attempt to mimic the functioning of the human nervous system. This branch of engineering attempts to mimic the biological structure of sensory and information-processing neural systems. In other words, neuromorphic computing implements various aspects of neurobiological networks in the form of analog and digital signals in electronic circuits. Neuromorphic computing has its roots in computational systems that were developed in the late 1980s and were designed to model the functioning of animal nervous systems. Since then, neuromorphic computing has gained momentum, to the point where some of the biggest names in technology have produced neuromorphic hardware. For example, IBM’s TrueNorth chip, Intel’s Loihi chip, and the Pohoiki Beach neuromorphic system are currently in production. Neuromorphics can do all of this without consuming a lot of energy, rather than leaving AI tasks to energy-hungry and cooling-intensive cloud systems. For neuromorphics to have a significant impact, there will need to be a lot of changes in the technology world. For example, sensor technologies are not designed to work well with neuromorphic systems and need to be redesigned to extract data in a way that can be processed by neuromorphic chips.

Graphical Abstract

Neuromorphic computing in Next Gen IT systems

Keywords

Subjects