IEEE Spectrum cover page article

By Max Versace | December 13, 2010

In december 2010, I have published a cover-page featured article on IEEE Spectrum, in collaboration with Ben Chandler, where we describe the roadmap to build intelligent machines with silicon synapses. In the article, we explain how the memristor-based approach will allow the building of brain-scale chips that mimic how neurons process information. The IEEE Spectrum magazineis the flagship publication of the IEEE, the world's largest professional technology association. It is a monthly magazine for technology innovators, business leaders, and the intellectually curious. Spectrum explores future technology trends and the impact of those trends on society and business. Read the article here.

IEEE Spectrum is read by over 385,000 technology professionals and senior executives worldwide in the high technology sectors of industry, government, and academia. Subscribers include engineering managers and corporate and financial executives.

The article is an outcome of the DARPA SyNAPSE (Systems of Neuromorphic Adaptive Plastic Scalable Electronics) project in collaboration with Hewlett-Packard. The SyNAPSE project was launched in late 2008 and aims to "investigate innovative approaches that enable revolutionary advances in neuromorphic electronic devices that are scalable to biological levels." DARPA has awarded funds to three prime contractors (HP, IBM, and HRL), with both HP and HRL working with Boston University researchers in the NSF-funded CELEST Science of Learning Center, where the Neuromorphics Lab is housed. In the article, Versace and Chandler talk about recent trends in bio-inspired computing, and how these are going to shape the future of neuroscience research and the computer industry in general. In particular, the article explains how technology based on memristors is enabling the manufacturingof new nanoscale computing devices. Memristors bring memory and computation close together by mimicking a neuron's synapses, which results in smaller, faster, and more efficient computer chips that can be used to implement brain-like computations in applications ranging from robotics to image processing to intelligent data analysis.