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
and JavaScript.
A flexible processor chip that has hardwired parameters for machine learning and contains around 1,000 logic gates can be built using a commercial 0.8-μm metal-oxide thin-film transistor technology. The schematic illustration on the cover highlights the flexible nature of the chips, which can be used in smart applications such as odour recognition.
Neuromorphic engineering attempts to create brain-like computing hardware and has helped reawaken interest in computer chip start-ups. But is the technology ready for mainstream application?
Circuits capable of reconfigurable logic and neuromorphic functions can be created by exploiting the electronic tunability of two-dimensional tungsten diselenide homojunctions.
This Review Article examines the development of spintronic devices for neuromorphic computing, exploring how magnetic tunnel junctions and magnetic textures can act as artificial neurons and synapses, as well as considering the challenges that exist in scaling up current systems.
This Review Article examines the development of neuro-inspired computing chips and their key benchmarking metrics, providing a co-design tool chain and proposing a roadmap for future large-scale chips.
A homojunction device made from two-dimensional tungsten diselenide can be used to create circuits that exhibit multifunctional logic and neuromorphic capabilities with simpler designs than conventional silicon-based systems.
A single ferroelectric field-effect transistor, which is made from ferroelectric hafnium oxide, can be used as a full-wave rectifier and frequency doubler.
A neurotransistor made from a silicon nanowire transistor coated by an ion-doped sol–gel silicate film can emulate the intrinsic plasticity of the neuronal membrane.
A memristor-based annealing system that uses an analogue neuromorphic architecture based on a Hopfield neural network can solve non-deterministic polynomial (NP)-hard max-cut problems in an approach that is potentially more efficient than current quantum, optical and digital approaches.
Using commercial 0.8-μm metal-oxide thin-film transistor technology, a flexible processor chip can be built that has hardwired parameters for machine learning and is capable of smart applications such as odour recognition.
A clock synchronization method, which is based on optical clock distribution and clock phase caching, can provide subnanosecond clock and data recovery times for fast optical switching in large-scale data centre networks using off-the-shelf commercial transceivers.
Neuromorphic engineering aims to create computing hardware that mimics biological nervous systems, and it is expected to play a key role in the next era of hardware development. Carver Mead recounts how it all began.