Ferroelectric Synaptic Transistor Network for Associative Memory

Abstract

Brain‐inspired associative memory is meaningful for pattern recognitions and image/speech processing. Here, a ferroelectric synaptic transistor network is proposed that is capable of associative learning and one‐step recalling of a whole set of data from only partial information. The competition between an external field and the internal depolarization field governs the ferroelectric creep of domain walls and offers each single ferroelectric synapse a full and subfemtojoule‐energy‐cost Hebbian synaptic plasticity, including short‐term memory (STM) to long‐term memory (LTM) transition, and remarkably both spike‐timing‐dependent plasticity (STDP) and spike‐rate‐dependent plasticity (SRDP). Assisted by the third terminal to control the ferroelectric domain dynamics, self‐adaptive coupling between neurons is realized by updating synaptic weight concurrently. Pavlov's dog experiment and multiassociative memories are demonstrated in this ferroelectric synaptic transistor network. Such ferroelectric synaptic transistor network is available for building multilayer neural networks and provides new avenues for associative‐memory information processing.

Ferroelectric photosensor network: an advanced hardware solution to real-time machine vision

“…Notably, the polarization switching can induce not only the magnitude change but also the sign reversal of photoresponse 19 , 21 , enabling a single FE-PS to represent both positive and negative weights and hence reducing the hardware overhead for network construction. Moreover, the nonvolatility, high controllability, and ultrafast switching kinetics (<1 ns) of polarization as demonstrated in various ferroelectric memory and neuromorphic devices 29 – 34 , along with the intimate coupling between polarization and photoresponse 35 , endow the FE-PS with good reliability and high write speed. Also noteworthy are the high photosensitivity and ultrashort photoresponse time (<1 ns) of FE-PS 24 , 25 , allowing a high-speed readout.…”

Mixed‐Dimensional Van der Waals Heterostructures Enabled Optoelectronic Synaptic Devices for Neuromorphic Applications

“…Inspired by the associate memory of the brain, associative learning, which is meaningful for pattern recognition and image/speech processing, is a process where memory can be recalled from its fragments or constituents by forming a connection between the environment and the organism's own reactions. [128] In other words, association can be built by experiencing two events together, leading to a connection of internal characteristics between these two events, which further indicates a fact that once one event is re-experienced, the other event will be also recalled. The associative learning has been well illustrated by Pavlov's dog experiment, [60] where the dog shows a slight response to simply bell-ring (Figure 11a) with the increase of PSC below the threshold for salivation.…”

“…After this training, a bell-ring stimulus can induce a salivation response (Figure 11d), which indicates an associative memory built between bell-ring and fool-sight. Recently, associative memory has been already proved in neuromorphic devices such as synaptic transistors [128] and memristors. [129,130] Cheng et al [131] reported a vertical 0D-perovskite/2D-MoS 2 MD vdW heterostructure-based phototransistor to emulate the photoelectric-synergistically typical associative learning (Figure 11e) and a receivable neural circuitry for associative learning is illustrated in Figure 11f, where the introduction of an interneuron enhances the interconnection between unconditioned stimulus (US) and conditioned stimulus (CS) from two different sensory neurons.…”

A Smarter Pavlovian Dog with Optically Modulated Associative Learning in an Organic Ferroelectric Neuromem

“…After conditioning, a response can be triggered for both the unconditioned and neutral stimuli, with the latter becoming a conditioned stimulus. Recently, memristive devices or circuits have been designed to implement associative learning behaviour at the hardware level [15][16][17][18][19][20][21][22][23][24]. However, enabling high tunability of associative learning in electronic devices as in biological counterparts, which is key to further advancing associative learning hardware, is still challenging.…”