Cascaded Architecture for Memristor Crossbar Array Based Larger-Scale Neuromorphic Computing

Sun, Siqi; Xu, Hui; Li, Jiwei; Li, Qingjiang; Liu, Haijun

doi:10.1109/access.2019.2915787

Cited by 12 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also verify the feasibility of our architecture on FASHION-MNIST dataset. From our experiments, the classification accuracy on this dataset achieves to 86.97%, which shows 2.71% decline compared with basic computation unit ( Sun et al, 2019b ), a conventional CNN with full precision.…”

Section: Introductionmentioning

confidence: 91%

Memristor Based Binary Convolutional Neural Network Architecture With Configurable Neurons

et al. 2021

Self Cite

View full text Add to dashboard Cite

The memristor-based convolutional neural network (CNN) gives full play to the advantages of memristive devices, such as low power consumption, high integration density, and strong network recognition capability. Consequently, it is very suitable for building a wearable embedded application system and has broad application prospects in image classification, speech recognition, and other fields. However, limited by the manufacturing process of memristive devices, high-precision weight devices are currently difficult to be applied in large-scale. In the same time, high-precision neuron activation function also further increases the complexity of network hardware implementation. In response to this, this paper proposes a configurable full-binary convolutional neural network (CFB-CNN) architecture, whose inputs, weights, and neurons are all binary values. The neurons are proportionally configured to two modes for different non-ideal situations. The architecture performance is verified based on the MNIST data set, and the influence of device yield and resistance fluctuations under different neuron configurations on network performance is also analyzed. The results show that the recognition accuracy of the 2-layer network is about 98.2%. When the yield rate is about 64% and the hidden neuron mode is configured as −1 and +1, namely ±1 MD, the CFB-CNN architecture achieves about 91.28% recognition accuracy. Whereas the resistance variation is about 26% and the hidden neuron mode configuration is 0 and 1, namely 01 MD, the CFB-CNN architecture gains about 93.43% recognition accuracy. Furthermore, memristors have been demonstrated as one of the most promising devices in neuromorphic computing for its synaptic plasticity. Therefore, the CFB-CNN architecture based on memristor is SNN-compatible, which is verified using the number of pulses to encode pixel values in this paper.

show abstract

Section: Introductionmentioning

confidence: 91%

Memristor Based Binary Convolutional Neural Network Architecture With Configurable Neurons

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Experiments are executed based on a 784 × 10 singlelayer perceptron (SLP) [29], a 784 × 100 × 10 multilayer perceptron (MLP) [30] and a ''3-2-1'' RRAM crossbar based cascaded architecture [12] which includes six convolutional neural networks. And each 28 × 28 handwritten image is converted to a 784 × 1 vector by voltage generator as the crossbar array input.…”

Section: B Calibration In Neuromorphic Computingmentioning

confidence: 99%

“…In order to further verify the performance of the calibration method which utilizes on multiply crossbar arrays cascaded, the cascaded architecture [12] is implemented with largescale memristor crossbar arrays. A ''3-2-1'' cascaded framework is utilized for simulation, which includes six basic computation units (BCU), and each BCU is a convolutional neural network.…”

Section: ) Cascaded Architecture On Crossbar Arraymentioning

confidence: 99%

See 1 more Smart Citation

Cases Study of Inputs Split Based Calibration Method for RRAM Crossbar

Sun

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Many mainstream applications require multiply-accumulate calculations, such as image processing and neuromorphic computing. Multiply-accumulate calculations using memristor crossbar arrays is a remarkable method for extremely high implementation efficiency, whereas the memristor array fabrication technology is still not mature and it is difficult to fabricate large-scale arrays with high-yield, which will seriously affect the performance of the application running on the RRAM crossbar. This paper proposes an inputs split based calibration method that improves the application accuracy in tolerating variations and stuck-at-fault of memristor devices. To demonstrate the performance of the calibration algorithm, the case of image sharpening and three neural networks architectures are applied for simulation experiments. And experimental results show that the calculation accuracy can be improved by up to 26.83% at 90% yield of crossbar arrays, and the success rate of the algorithm can be as high as 99.3% when there are several arrays cascaded. It is of great significance to the application of arrays in multiply-accumulate computation.

show abstract

“…Memristor crossbar arrays with a possible 3-D architecture seem suitable to realize the high connectivity of a brain's neuronal system [14], [15]. Recently, memristor crossbar arrays have been suggested as a way to achieve high cost-and energy-efficient implementation of artificial neural networks [16]- [20]. To realize the signed synaptic weights, two memristor crossbar arrays are employed [19]- [21].…”

Section: Introductionmentioning

confidence: 99%

Single Crossbar Array of Memristors With Bipolar Inputs for Neuromorphic Image Recognition

Truong

2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose a new crossbar architecture of memristors with bipolar inputs for an image recognition application. The performance of the proposed crossbar array with bipolar inputs is based on the simplified Exclusive-NOR function to measure the similarity between the input pattern and the stored patterns. In the proposed architecture, only one crossbar array is used instead of two crossbar arrays. The number of memristors in the proposed architecture is reduced by 50%, when compared to the complementary and the twin architectures. The proposed crossbar architecture with bipolar inputs consumes 16.7% and 7.2% less power than do the complementary and twin architectures. In addition, using only one crossbar array in the proposed architecture can improve the fault tolerance of the crossbar circuit. When 10% of memristors are defective, the proposed crossbar architecture shows a recognition rate improved by 5%, 7% and 4% over that of the memristor binarized neural network, the complementary architecture of the memristor crossbar and the twin architecture of the memristor crossbar when recognizing 10 images.

show abstract

Cascaded Architecture for Memristor Crossbar Array Based Larger-Scale Neuromorphic Computing

Cited by 12 publications

References 23 publications

Memristor Based Binary Convolutional Neural Network Architecture With Configurable Neurons

Memristor Based Binary Convolutional Neural Network Architecture With Configurable Neurons

Cases Study of Inputs Split Based Calibration Method for RRAM Crossbar

Single Crossbar Array of Memristors With Bipolar Inputs for Neuromorphic Image Recognition

Contact Info

Product

Resources

About