A non-linear two-dimensional float gate transistor as a lateral inhibitory synapse for retinal early visual processing.

Synaptic transistors that accommodate concurrent signal transmission and learning in a neural network are attracting enormous interest for neuromorphic sensory processing. To remove redundant sensory information while keeping important features, artificial synaptic transistors with non-linear conductance are desired to apply filter processing to sensory inputs. Here, we report the realization of non-linear synapses using a two-dimensional van der Waals (vdW) heterostructure (MoS2/h-BN/graphene) based float gate memory device, in which the semiconductor channel is tailored via a surface acceptor (ZnPc) for subthreshold operation. In addition to usual synaptic plasticity, the memory device exhibits highly non-linear conductance (rectification ratio >106), allowing bidirectional yet only negative/inhibitory current to pass through. We demonstrate that in a lateral coupling network, such a float gate memory device resembles the key lateral inhibition function of horizontal cells for the formation of an ON-center/OFF-surround receptive field. When combined with synaptic plasticity, the lateral inhibition weights are further tunable to enable adjustable edge enhancement for early visual processing. Our results here hopefully open a new scheme toward early sensory perception via lateral inhibitory synaptic transistors.

Enhancing LiAlOX synaptic performance by reducing the Schottky barrier height for deep neural network applications.

Although good performance has been reported in shallow neural networks, the application of memristor synapses towards realistic deep neural networks has met more stringent requirements on the synapse properties, particularly the high precision and linearity of the synaptic analog weight tuning. In this study, a LiAlOX memristor synapse was fabricated and optimized to address these demands. By delicately tuning the initial conductance states, 120-level continuously adjustable conductance states were obtained and the nonlinearity factor was substantially reduced from 8.96 to 0.83. The significant enhancements were attributed to the reduced Schottky barrier height (SBH) between the filament tip and the electrode, which was estimated from the measured I-V curves. Furthermore, a deep neural network for realistic action recognition task was constructed, and the recognition accuracy was found to be increased from 15.1% to 91.4% on the Weizmann video dataset by adopting the above-described device optimization method.

Nanochannel-Based Transport in an Interfacial Memristor Can Emulate the Analog Weight Modulation of Synapses.

By exploiting novel transport phenomena such as ion selectivity at the nanoscale, it has been shown that nanochannel systems can exhibit electrically controllable conductance, suggesting their potential use in neuromorphic devices. However, several critical features of biological synapses, particularly their conductance modulation, which is both memorable and gradual, have rarely been reported in these types of systems due to the fast flow property of typical inorganic electrolytes. In this work, we demonstrate that electrically manipulating the nanochannel conductance can result in nonvolatile conductance tuning capable of mimicking the analog behavior of synapses by introducing a room-temperature ionic liquid (IL) and a KCl solution into the two ends of a nanochannel system. The gradual conductance-tuning mechanism is identified through fluorescence measurements as the voltage-induced movement of the interface between the immiscible IL and KCl solution, while the successful memorization of the conductance tuning is ascribed to the large viscosity of the IL. We applied a nanochannel-based synapse to a handwritten digit-recognition task, reaching an accuracy of 94%. These promising results provide important guidance for the future design of nanochannel-based neuromorphic devices and the manipulation of nanochannel transport for computing.