Search

The recent emergence of the hybrid quantum-classical neural network (HQCNN) architecture has garnered considerable attention because of the potential advantages associated with integrating quantum principles to enhance various facets of machine learning algorithms and computations. However, the current investigated serial structure of HQCNN, wherein information sequentially passes from one network to another, often imposes limitations on the trainability and expressivity of the network. In this study, we introduce a novel architecture termed parallel proportional fusion of spiking and quantum neural networks (PPF-SQNN). The dataset information is simultaneously fed into both the spiking neural network and the variational quantum circuits, with the outputs amalgamated in proportion to their individual contributions. We systematically assess the impact of diverse PPF-SQNN parameters on network performance for image classification, aiming to identify the optimal configuration. On three datasets for image classification tasks, the final classification accuracy reached 98.2%, 99.198%, and 97.921%, respectively, with loss values all below 0.2, outperforming the compared serial networks. In noise testing, it also demonstrates good classification performance even under noise intensities of 0.9 Gaussian and uniform noise. This study introduces a novel and effective amalgamation approach for HQCNN, laying the groundwork for the advancement and application of quantum advantages in artificial intelligence computations. [ABSTRACT FROM AUTHOR]

Memristor, with the ability of analog computing, is widely investigated for improving the computing efficiency of deep neural networks (DNNs) deployment. However, how to fully take advantage of the analog computing ability of memristive computing system (MCS) for DNN deployment is still an open question. Here, a new neural network models deployment scheme, that is, an information dimension matching (IDM) scheme, is proposed to fully take advantage of the analog computing ability of MCS. Furthermore, the spatial and temporal DNN, that is convolutional neural network (CNN) and recurrent neural network (RNN) is used to verify the proposed deployment scheme, respectively. The experimental results indicate that, compared to the traditional deployment schemes, the proposed deployment scheme shows obvious inference accuracy and energy efficiency improvement (>4 × in four‐layer DNNs deployment), and the energy efficiency improvement increases dramatically with the layers increment of DNNs. This work paves the path for developing high computing efficiency analog MCS. [ABSTRACT FROM AUTHOR]

In this article, we analyzed the experimental data based on the TaOx memristor and found that the threshold switching (TS) characteristics are related to temperature, and its logarithmic I–V curve is in good agreement with the space charge limiting current conduction mechanism. We use this mechanism to establish a TS physical model and then use the physical model to build an LTspice model. The model data are fitted with the experimental data, which is basically consistent. Next, using the TS memristor to simulate a leaky integrate-and-fire neuron circuit, the basic dynamics are realized. By changing the external temperature of the memristor, the output frequency of the neuron will be more intense as the temperature increases. Finally, an artificial spiking neural network (SNN) was built based on this neuron circuit for MNIST recognition task. In this SNN, the input signals fused both voltage amplitude and temperature to achieve neuromorphic multimodal preprocessing and enhance the recognition accuracy. These results demonstrated the reliability of the model, which enhanced the flexibility for exploring the application of TaOx-based TS memristors. [ABSTRACT FROM AUTHOR]

A memristive neuron circuit which is capable of encoding input information via temporal and adaptive frequency methods within the same structure is proposed. Its multifunctionality allows switching between these modes by adjusting circuit capacitors. Furthermore, it is investigated how other parameters like input voltage and resistance influence output properties for different encoding methods. This research contributes to the development of more flexible neuromorphic computing systems. [ABSTRACT FROM AUTHOR]

A more accurate synaptic modeling based on oxygen vacancy conductive mechanism is presented in this paper. Two internal state variables, that is, the length and area of conductive region, are used to describe the vertical and lateral growth/dissolution dynamics of the region, based on the physical mechanisms of ion drift and two different diffusion effects. Since the effect of length on the electric field is not negligible, it is introduced into the modeling. In addition, the Fick and Soret diffusions are considered, because they cause the model to produce a "forgetting" property and a "memory" retention. By the comparisons, this modeling captures the actual device better than others. In addition, the previous models can be derived from this one. Some rough analysis suggests that the modeling possibly captures different memristors by adjusting the parameters, and the effects of oxygen concentration and temperature on synapse can also be considered. Therefore, this modeling is more comprehensive and generalized. Several important synaptic functions are simulated, including excitatory postsynaptic current, paired‐pulse facilitation, spike‐rate‐dependent plasticity, and spike‐timing‐dependent plasticity, which may provide a theoretical basis for some potential applications such as artificial neural networks and artificial intelligence. [ABSTRACT FROM AUTHOR]