Search

The authors demonstrate the use of standing waves to generate localised heat using nanoantennae in integrated photonics. They utilise this heat to mediate all-photonic integration of 50 GHz optical signals, showing experimentally, the potential for achieving programmable nonlinear activation functions. This is a step towards full optical encoding in integrated photonic processors.

Here stable colour changes induced by solid-state electrical switching of ultrathin films of a germanium–antimony–telluride alloy are demonstrated, adding to its established uses in data storage; possible applications include flexible and transparent displays.

A photonic computing platform using chaotic light for probabilistic arithmetic enables ultrafast, parallel processing. The system predicts classification and uncertainty simultaneously. The optical architecture allows efficient distribution evaluations at each output in a single time step.

Two photonic platforms using a convolutional processing system with partially coherent light sources is shown to boost computing parallelism, demonstrated using the classification of gaits of patients with Parkinson’s disease and the MNIST handwritten digits dataset.

Atomically thin heterostructures function as optomemristors, which are used for biomimetic neural algorithms for performing winner-take-all tasks, such as competitive and cooperative learning.

Hybrid photonic–electronic systems are essential for high-throughput neuromorphic computing. Here, the authors report an in-memory photonic–electronic dot-product engine with decoupled electronic programming of the phase-change memory cells and parallel photonic computation with high-bit operation, low energy consumption, and high accuracy.

Some types of machine learning rely on the interaction between multiple signals, which requires new devices for efficient implementation. Here, Sarwat et al demonstrate a memristor that is both optically and electronically active, enabling computational models such as three factor learning.

Direct modulation of Young‟s Modulus to affect mechanical resonances in real-time has not been achieved before. Here, the authors leverage the dislocation migration phenomenon in GeTe nanowires to develop nanoelectromechanical systems with powerfree tuning of mechanical resonances within a range of 30%, high and stable quality and gauge factors.

The memristor, in which an external electric field controls the formation and annihilation of conductive channels, has been described both as a missing electronic element and a memory and computational element. Here, their utility as building blocks for promising reflective and energy-efficient colour technology is described.

Physical computing, particularly photonic computing, offers a promising alternative by directly encoding data in physical quantities, enabling efficient probabilistic computing. This Perspective discusses the challenges and opportunities in photonic probabilistic computing and its applications in artificial intelligence.

Ultrasharp scanning probe microscope tips made of diamond-like carbon that contains silicon and oxygen demonstrate very high levels of wear resistance.

Radio-frequency modulation of optical signals increase the parallelization of photonic processors beyond that afforded by exploiting spatial and wavelength dimensions alone. The approach is then demonstrated on electrocardiogram signals and identifies patients at sudden death risk with 93.5% accuracy.

An integrated photonic processor, based on phase-change-material memory arrays and chip-based optical frequency combs, which can operate at speeds of trillions of multiply-accumulate (MAC) operations per second, is demonstrated.

Neuromorphic photonics is an emerging computing platform that addresses the growing computational demands of modern society. We review advances in integrated neuromorphic photonics and discuss challenges associated with electro-optical conversions, implementations of nonlinearity, amplification and processing in the time domain.

Researchers use phase-change materials to demonstrate an integrated optical memory with 13.4 pJ switching energy.

Optical analogues of electronic memristors are desirable for applications including photonic artificial intelligence and computing platforms. Here, recent progress on integrated optical memristors is reviewed.

Multidimensional photonic computing is a framework that combines classical and quantum approaches, leveraging the properties of light. This Perspective explores its potential to enable scalable, neuromorphic photonic quantum systems suited to data-intensive and complex computational tasks.

Photonics offers an attractive platform for implementing neuromorphic computing due to its low latency, multiplexing capabilities and integrated on-chip technology.