Neuromorphic Imaging: Fully Light‐Controlled Memory and Neuromorphic Computation in Layered Black Phosphorus (Adv. Mater. 10/2021)

Abstract

An all‐optically tunable neuromorphic imaging element based on black phosphorus (BP) is demonstrated by Taimur Ahmed, Sumeet Walia, and co‐workers in article number 2004207. The unusual wavelength‐dependent photocurrent in BP is harnessed to optically program and erase visual memory elements. Concurrently, the same elements are capable of in‐pixel image preprocessing in an imaging array and optoelectronic machine learning for pattern classification and image recognition through deploying artificial neural networks.

Fully Photon Controlled Synaptic Memristor for Neuro‐Inspired Computing

“…Due to the physical separation of data storage and processing units, von Neumann architecture based conventional computing systems are facing the great challenges of high energy All-optically modulated artificial synapses [9,[22][23][24][25][26][27] have been reported in previous works and listed in the Table 1, where excitatory and inhibitory synaptic behaviors have been exhibited in an all-optically pathway by applying a wide range of light spectra from UV to Infrared. Hu et al recently reported IGZO thin films based bilayer structured (homo-junction) synaptic memristor, [22] where the blue and near infra-red (NIR) light pulses were used for optical SET and RESET behaviors, respectively, in the same device.…”

“…Some analogous issues of computational latency, higher energy consumption, and hardware redundancy could occur in those devices owing to bandwidth connection density trade-off. [9,10] Such kind of problems make them less tempting. The cognizance of fully photon modulated synaptic memristor was getting researchers' attention in an impressive manner because they can get over the above mentioned issues with the benefits of ultra-fast operation speed, no electrical interconnect power losses, and high bandwidth.…”

“…The cognizance of fully photon modulated synaptic memristor was getting researchers' attention in an impressive manner because they can get over the above mentioned issues with the benefits of ultra-fast operation speed, no electrical interconnect power losses, and high bandwidth. [9,11,12] Therefore, a fully light stimulated synaptic device is highly desired.…”

Concept of Photoactive Invisible Inks toward Ultralow‐Cost Fabrication of Transistor Photomemories

“…The development of photonic nonvolatile transistor memories has captured a great deal of interest owing to the more energy saving, ultrafast information processing, low noise interferences, and better security levels compared to conventional electrically controlled one. [1] In addition, transistor photomemory devices have given birth to many potential applications such as, pulse monitoring device, [2] ultrasensitive photodetector, [3] photorecorder, [4] image identification, [5] artificial synapse, [6] and next-generation big data storage [7] that could critically support the rapid growth of artificial intelligence (AI) [8] and Internet of Things (IoTs) [9] in nowadays digital era. Utilizing various light wavelengths, intensities, and exposure times (in combination with continuous or pulse mode) in the device operations, [1d] the memory behaviors of such devices could be precisely controlled, extending the versatilities of transistor photomemories as a supreme building block toward neuromorphic computing [10] and multibit memory cell.…”

One‐Phototransistor–One‐Memristor Array with High‐Linearity Light‐Tunable Weight for Optic Neuromorphic Computing

“…DOI: 10.1002/adma.202204844 vision architecture, optic neuromorphic devices like photonic memristors, [7][8][9][10][11][12][13][14][15][16][17][18] have been developed for use as neuromorphic vision sensors, and they have shown great promise in combining optic sensing, memory, and processing functions in the same device. [4,17,[19][20][21] Therefore, preprocessing and computing of the images in vision sensors can be efficiently realized at the edge rather than in cloud sever systems.…”