A modal learning adaptive function neural network applied to handwritten digit recognition

Highly Controllable and Silicon-Compatible Ferroelectric Photovoltaic Synapses for Neuromorphic Computing

Ferroelectric synapses using polarization switching (a purely electronic switching process) to induce analog conductance change have attracted considerable interest. Here, we propose ferroelectric photovoltaic (FePV) synapses that use polarization-controlled photocurrent as the readout and thus have no limitations on the forms and thicknesses of the constituent ferroelectric and electrode materials. This not only makes FePV synapses easy to fabricate but also reduces the depolarization effect and hence enhances the polarization controllability. As a proof-of-concept implementation, a Pt/Pb(Zr_0.2Ti_0.8)O₃/LaNiO₃ FePV synapse is facilely grown on a silicon substrate, which demonstrates continuous photovoltaic response modulation with good controllability (small nonlinearity and write noise) enabled by gradual polarization switching. Using photovoltaic response as synaptic weight, this device exhibits versatile synaptic functions including long-term potentiation/depression and spike-timing-dependent plasticity. A simulated FePV synapse-based neural network achieves high accuracies (>93%) for image recognition. This study paves a new way toward highly controllable and silicon-compatible synapses for neuromorphic computing.

CHINESE LICENSE PLATE RECOGNITION BASED ON HUMAN VISION ATTENTION MECHANISM

License plate recognition (LPR) is one of the most important elements affecting intelligent transportation systems. A number of LPR techniques have been proposed. Humans are good target recognition systems. In other words, humans easily recognize common objects. In this paper, the researchers present a novel method of recognizing Chinese license plates. The method is based on the Human Vision Attention Mechanism (HVAM) and uses Chinese license plates as the targets. The research consists of three stages. The first stage involved finding and identifying license plates in videos of moving vehicles. The second stage separated each license plate into the seven characters. In the third stage, the character recognizer extracted some salient features of Chinese characters and used a multi-stage classifier to recognize each character on the license plate. In the experiment locating license plates, 1176 images taken from various scenes and conditions were employed. The method failed to identify the license plates in only 27 of the images; resulting in a license plate location rate of success of 97.7%. In the experiment for identifying license characters, 1149 images were used, from which license plates had been successfully located. The method failed to identify the characters in 45 of these images giving a success rate of 96.1%. Combining the above two rates, the overall rate of success for our LPR is 93.9%.