Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
By integrating a memristor crossbar array with complementary metal–oxide–semiconductor (CMOS) control circuitry, a programmable neuromorphic computing chip can be created that is capable of efficient multiply–accumulate operations. The cover shows an optical microscopy image of the integrated chip, with the 54 × 108 crossbar array at the centre.
An integrated co-processor chip based on a memristor crossbar array and complementary metal–oxide–semiconductor (CMOS) control circuitry can be used to implement neuromorphic and machine learning algorithms.
This Review Article examines the development of two-dimensional spintronics for low-power electronics, exploring potential devices and circuits, as well the challenges that exist in delivering practical applications.
A programmable neuromorphic computing chip based on passive memristor crossbar arrays integrated with analogue and digital components and an on-chip processor enables the implementation of neuromorphic and machine learning algorithms.
Thermoelectric generators based on nanostructured silicon thermopiles, which are fabricated on an industrial silicon CMOS process line and are thus compatible with integrated circuit technology, exhibit a high specific power generation capacity of up to 29 μW cm−2 K−2 near room temperature.
Quantum-mechanical band-to-band tunnelling can be used to create an energy-efficient ternary logic technology that can be fabricated on the wafer scale using complementary metal–oxide–semiconductor (CMOS) processes.