Flexible Neural Network Realized by the Probabilistic SiOx Memristive Synaptic Array for Energy-Efficient Image Learning

The human brain's neural networks are sparsely connected via tunable and probabilistic synapses, which may be essential for performing energy-efficient cognitive and intellectual functions. In this sense, the implementation of a flexible neural network with probabilistic synapses is a first step toward realizing the ultimate energy-efficient computing framework. Here, inspired by the efficient threshold-tunable and probabilistic rod-to-rod bipolar synapses in the human visual system, a 16 x 16 crossbar array comprising the vertical form of gate-tunable probabilistic SiOx memristive synaptic barristor utilizing the Si/graphene heterojunction is designed and fabricated. Controllable stochastic switching dynamics in this array are achieved via various input voltage pulse schemes. In particular, the threshold tunability via electrostatic gating enables the efficient in situ alteration of the probabilistic switching activation (P-Act) from 0 to 1.0, and can even modulate the degree of the P-Act change. A drop-connected algorithm based on the P-Act is constructed and used to successfully classify the shapes of several fashion items. The suggested approach can decrease the learning energy by up to approximate to 2,116 times relative to that of the conventional all-to-all connected network while exhibiting a high recognition accuracy of approximate to 93 %.

Automated summary

This study focuses on the implementation of a flexible neural network with probabilistic synapses as a first step towards an ultimate energy-efficient computing framework. A 16x16 crossbar array is designed and fabricated, utilizing a threshold-tunable and probabilistic SiOx memristive synaptic barristor with Si/graphene heterojunction. The suggested approach achieves significant reduction in learning energy while maintaining a high recognition accuracy.