A progressive surrogate gradient learning for memristive spiking neural network

In recent years, spiking neural networks(SNNs) have received increasing attention of research in the field of artificial intelligence due to their high biological plausibility, low energy consumption, and abundant spatio-temporal information.However, the non-differential spike activity makes SNNs more difficult to train in supervised training. Most existing methods focusing on introducing an approximated derivative to replace it, while they are often based on static surrogate functions. In this paper, we propose a progressive surrogate gradient learning for backpropagation of SNNs, which is able to approximate the step function gradually and to reduce information loss. Furthermore, memristor cross arrays are used for speeding up calculation and reducing system energy consumption for their hardware advantage. The proposed algorithm is evaluated on both static and neuromorphic datasets using fully connected and convolutional network architecture, and the experimental results indicate that our approach has a high performance compared with previous research.

Pulse coding off-chip learning algorithm for memristive artificial neural network

Memristive neural network has attracted tremendous attention since the memristor array can perform parallel multiplyaccumulate calculation(MAC)operations and memory-computation operations as compared with digital CMOS hardware systems.However,owing to the variability of the memristor,the implementation of high-precision neural network in memristive computation units is still difficult.Existing learning algorithms for memristive artificial neural network(ANN)is unable to achieve the performance comparable to high-precision by using CMOS-based system.Here,we propose an algorithm based on off-chip learning for memristive ANN in low precision.Training the ANN in the high-precision in digital CPUs and then quantifying the weight of the network to low precision,the quantified weights are mapped to the memristor arrays based on VTEAM model through using the pulse coding weight-mapping rule.In this work,we execute the inference of trained 5-layers convolution neural network on the memristor arrays and achieve an accuracy close to the inference in the case of high precision(64-bit).Compared with other algorithms-based off-chip learning,the algorithm proposed in the present study can easily implement the mapping process and less influence of the device variability.Our result provides an effective approach to implementing the ANN on the memristive hardware platform.

Memristor-based hyper-chaotic circuit for image encryption

The memristor is a kind of non-linear element with memory function,which can be applied to chaotic systems to increase signal randomness and complexity.In this paper,a new four-dimensional hyper-chaotic system is designed based on a flux controlled memristor model,which can generate complex chaotic attractors.The basic dynamic theory analysis and numerical simulations of the system,such as the stability of equilibrium points,the Lyapunov exponents and dimension,Poincare maps,the power spectrum,and the waveform graph prove that it has rich dynamic behaviors.Then,the circuit implementation of this system is established.The consistency of simulation program with integrated circuit emphasis(SPICE)simulation and numerical analysis proves the ability to generate chaos.Finally,a new image encryption scheme is designed by using the memristor-based hyper-chaotic system proposed in this paper.The scheme involves a total of two encryptions.By using different security analysis factors,the proposed algorithm is compared with other image encryption schemes,including correlation analysis,information entropy,etc.The results show that the proposed image encryption scheme has a large key space and presents a better encryption effect.