Linear conductance update improvement of CMOS-compatible second-order memristors for fast and energy-efficient training of a neural network using a memristor crossbar array

Abstract

Memristors are two-terminal memory devices that can change conductance state and store analog values. Thanks to their simple structure, suitability for high-density integration, and non-volatile characteristics, memristors have been intensively...

High on/off ratio SiO2-based memristors for neuromorphic computing: understanding the switching mechanisms through theoretical and electrochemical aspects

“…, dynamic range) where the conduction filament experiences thickening (potentiation) and shrinkage (depression). 49 To validate this proposed switching mechanism, the retention (Fig. S13a and b, ESI†) and EIS (Fig.…”

Unveiling transient current response in bilayer oxide-based physical reservoirs for time-series data analysis

“…The fitting parameters α, β, γ, δ, λ, η, τ in eqn (1) and ( 2) are provided in Table S2. † To simulate device responses to input pulses, the pulse parameters such as voltage amplitude, width, and pulse interval are used in eqn ( 1) and (2) The schematic diagram of the relocation of oxygen vacancies is shown in Fig. 2a to illustrate the memristor model.…”

“…Artificial neural networks (ANNs) are designed to mimic the structure and functionality of biological neural networks found in the human brain. 1–3 The nervous system comprises billions of interconnected neurons that communicate via electrical and chemical signals. 4,5 These neurons are organized into complex networks that can process and integrate a vast amount of information, learn from experience, and adapt to new situations.…”

From Oxides to 2D Materials: Advancing Memristor Technologies for Energy-Efficient Neuromorphic Computing

“…In practical scenarios, the modulation of memristor conductance often entails the application of multiple electrical pulses that vary in number, duration, and amplitude. 72 The challenge arises from the necessity of accounting for the cumulative energy impact of all of the pulses involved in the switching process. Furthermore, the incorporation of writeand-verify algorithms managed by external circuits or microprocessors 73 complicates energy consumption assessment.…”

“…However, this straightforward calculation does not encapsulate the complexities prevalent in real-world applications. In practical scenarios, the modulation of memristor conductance often entails the application of multiple electrical pulses that vary in number, duration, and amplitude . The challenge arises from the necessity of accounting for the cumulative energy impact of all of the pulses involved in the switching process.…”