A sensory memory processing system with multi-wavelength synaptic-polychromatic light emission for multi-modal information recognition

Abstract

Realizing multi-modal information recognition tasks which can process external information efficiently and comprehensively is an urgent requirement in the field of artificial intelligence. However, it remains a challenge to achieve simple structure and high-performance multi-modal recognition demonstrations owing to the complex execution module and separation of memory processing based on the traditional complementary metal oxide semiconductor (CMOS) architecture. Here, we propose an efficient sensory memory processing system (SMPS), which can process sensory information and generate synapse-like and multi-wavelength light-emitting output, realizing diversified utilization of light in information processing and multi-modal information recognition. The SMPS exhibits strong robustness in information encoding/transmission and the capability of visible information display through the multi-level color responses, which can implement the multi-level pain warning process of organisms intuitively. Furthermore, different from the conventional multi-modal information processing system that requires independent and complex circuit modules, the proposed SMPS with unique optical multi-information parallel output can realize efficient multi-modal information recognition of dynamic step frequency and spatial positioning simultaneously with the accuracy of 99.5% and 98.2%, respectively. Therefore, the SMPS proposed in this work with simple component, flexible operation, strong robustness, and highly efficiency is promising for future sensory-neuromorphic photonic systems and interactive artificial intelligence.

Cross-layer transmission realized by light-emitting memristor for constructing ultra-deep neural network with transfer learning ability

“…Furthermore, once the hardware network is constructed, changing weights becomes extremely costly as the weights are typically expressed using transmittance, which is fixed and unchangeable. Furthermore, despite some efforts have proposed artificial luminescent synapses, these devices only employed one output (optical or electrical signal) for transmission in the neural network, failing to propose effective strategies to leverage the dual-output potential of devices and achieve powerful networks 13 , 34 , 43 . Hence, a strategy utilizing dual-output characteristics of N-LEM to construct cross-layer transmission block (ClBlock) was proposed to achieve an ultra-deep photoelectric neural network (UPENN) and ultra-deep super-resolution reconstruction neural network (USRNN) with transfer learning ability (Fig.…”

Feedforward Photoadaptive Organic Neuromorphic Transistor with Mixed‐Weight Plasticity for Augmenting Perception

“…It is found that the surface potential increase and then decrease after irradiation compared to dark, and the degree of decay increases with increasing light intensity. Given that the decrease (increase) of the film surface potential is correlated with the increase (decrease) of the film electron concentration, [17] from a field effects perspective, the effect of the V GS on the channel modulation is diminished by some factor when the device is subject to irradiation.…”

Flexible Optoelectronic Synapses Based on Conjugated Polymer Blends for Ultra Broadband Spectrum Light Perception

“…Modulation of pulse frequency is also important for neuronal functioning . As shown in Figure a, under DUV light stimulation, when the light pulse frequency was increased from 0.5 to 10 Hz, the EPSC was gradually increased from 8.77 to 11.09 nA, and good regulation was achieved.…”