New weapons systems to mimic human brain


WEAPONS systems with the intelligence of human brains could be reality soon, if Defense Advanced Research Projects Agency (DARPA) gets its way.

DARPA has announced that it is working to build electronic neural architectures that can learn, adapt and respond to situations on the battlefield.

Currently, unmanned systems and electronic devices can collect and process information according to their programming.

DARPA’s Systems of Neuromorphic Adaptive Plastic Scalable Electronics (aptly shortened to SyNAPSE) program aims to develop biological-scale neuromorphic electronic systems that mimic important functions of a human brain.

Applications for neuromorphic electronics include robotic and manned systems, and sensory and integration applications such as image processing.

These human brain-inspired electronic systems will understand, adapt and respond to information in fundamentally different ways than traditional computers.

Unlike current computers with distinct processor and memory units, these new systems will, like the brain, be organised as an intimate and distributed web of very simple processors (neurons) and memory (synapses) that spontaneously communicate and learn their functions.

SyNAPSE is developing integrated circuits with high densities of electronic devices and integrated communication networks that approximate the function and connectivity of neurons and synapses.

The DARPA program has also developed tools to support this specific area of hardware development such as circuit design tools, large-scale computer simulations of hardware function, and virtual training environments that can test and benchmark these systems.

Thus far, the program has developed nanometer-scale synaptic components capable of adapting the connection strength between two electronic neurons, and simulating utility of these components in core microcircuits that support the overall system architecture.

Goals for the upcoming phase include chip-fabrication process development, design and validation of single-chip systems, and demonstration of these systems in virtual environments that emphasize behavioural tasks related to navigation and perception.