Long short-term memory (LSTM) with significantly increased complexity and a large number of parameters have a bottleneck in computing power resulting from limited memory capacity. Hardware acceleration of LSTM using memristor circuit is an effective solution. This paper presents a complete design of memristive LSTM network system. Both the LSTM cell and the fully connected layer circuit are implemented through memristor crossbars, and the 1T1R design avoids the influence of the sneak current which helps to improve the accuracy of network calculation. To reduce the power consumption, the word embedding dimensionality was reduced using the GloVe model, and the number of features in the hidden layer was reduced. The effectiveness of the proposed scheme is verified by performing the text classification task on the IMDB dataset and the hardware training accuracy reached as high as 88.58%.

Most operant conditioning circuits predominantly focus on simple feedback process, few studies consider the intricacies of feedback outcomes and the uncertainty of feedback time. This paper proposes a neuromorphic circuit based on operant conditioning with addictiveness and time memory for automatic learning. The circuit is mainly composed of hunger output module, neuron module, excitement output module, memristor-based decision module, and memory and feedback generation module. In the circuit, the process of output excitement and addiction in stochastic feedback is achieved. The memory of interval between the two rewards is formed. The circuit can adapt to complex scenarios with these functions. In addition, hunger and satiety are introduced to realize the interaction between biological behavior and exploration desire, which enables the circuit to continuously reshape its memories and actions. The process of operant conditioning theory for automatic learning is accomplished. The study of operant conditioning can serve as a reference for more intelligent brain-inspired neural systems.

A physical ${\text{Sr}}_{0.95}{\text{Ba}}_{0.05}{\text{TiO}}_3$ memristor-based modified Chua’s circuit is proposed, which is studied in this paper by means of both theoretical analysis and numerical simulations. The stability of this memristor-based modified Chua’s circuit is analyzed. A systematic investigation of the dynamic behaviors and their dependence on the initial states and circuit parameters is performed, presenting the Lyapunov exponents spectra, bifurcation diagrams, phase diagrams, and Poincaré maps. The circuit emerges multiple dynamic behaviors, including stable points, periodic cycles, chaos, and some transient chaos. Specifically, the system has multistability, i.e., coexisting periods and coexisting chaotic attractors with the change of initial states and circuit parameters. This study is conducive to the subsequent design and analysis of memristor-based circuits for potential practical applications.

Most memristive bionic circuits focus on how to realize bionic functions, few studies consider the biomimetic of the circuit structure and operation rules, so it is difficult to learn, memorize, and make decisions as biological neural networks. In this work, a multifunctional neuromorphic circuit inspired by tunable neural circuitry motifs is proposed. The circuit is more closely with biological characteristics in both structure and functions, which is designed based on neural circuit architectures. By connecting different neural circuitry motifs, the circuit realizes operant conditioning functions such as random exploration, behavioral frequency modulation, and decision-making. Also, the circuit integrated classical conditioning and operant conditioning in order to mimic the decision-making process, which was driven by the association of secondary and primary stimuli. In addition, the factors influencing decision-making are researched, such as the rates of learning and forgetting, and the conversion of short-term to long-term memory. The operational results of the proposed circuits in LTspice show that they can mimic the aforementioned functions, which have advantages in bionicity and scalability. This work can be applied in intelligent robotic platforms to achieve exploration and rescue in complex environments.

The Sr_0.95Ba_0.05TiO₃ (SBT) nanometer film is prepared on the commercially available Pt/TiO₂/SiO₂/Si substrate by radio-frequency magnetron sputtering. The x-ray diffraction pattern and the scanning electron microscope image of the cross-sectional profile of the SBT nanometer film are depicted. The memristive mechanism is inferred. The mathematical model is calculated, where M(q) denotes the memristance depending on the quantity of electric charge, and q(t) denotes the quantity of electric charge depending on the time. The theoretical I–V characteristics of the SBT nanometer film are obtained by the mathematical model. The results show that the theoretical I–V characteristics are consistent with the measured I–V characteristics. Moreover, the mathematical model could guide the research on applications of the memristor.