Design of memristor-based image convolution calculation in convolutional neural network

Zeng, Xiaofen; Wen, Shiping; Zeng, Zhigang; Huang, Tingwen

doi:10.1007/s00521-016-2700-2

Cited by 50 publications

(23 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a kind of deep learning neural network, several powerful applications of CNNs were reported including pattern recognition and classification, such as human face recognition [31], traffic sign recognition [32], and object recognition [33]. Recently, in the field of image classification accuracy, convolution neural network (CNN) achieved a state-of-the art result, which can classify more than a million images into 1000 different classes [29,34,35]. Compared with traditional neural networks, such as fully connected NN, where each neuron is connected to all neurons of the prelayer via a large number of synapses,convolutional neural networks take advantages in weight sharing, which reduces the number of parameters need to be trained [29].…”

Section: Cnn Conceptsmentioning

confidence: 99%

“…A classical architecture of convolutional neural network was first proposed by Lecun et al [29,30]. As a kind of deep learning neural network, several powerful applications of CNNs were reported including pattern recognition and classification, such as human face recognition [31], traffic sign recognition [32], and object recognition [33].…”

Section: Cnn Conceptsmentioning

confidence: 99%

“…This operation could extract different features of input images when using different convolutional kernels [29]. The input image signal will have dot product operation with kernel, and through the nonlinear transformation, the final output feature map.…”

Section: Cnn Architecturesmentioning

confidence: 99%

“…Recently, in the field of image classification accuracy, convolution neural network (CNN) achieved a state-of-the art result, which can classify more than a million images into 1000 different classes [29,34,35]. Compared with traditional neural networks, such as fully connected NN, where each neuron is connected to all neurons of the prelayer via a large number of synapses,convolutional neural networks take advantages in weight sharing, which reduces the number of parameters need to be trained [29]. CNNs are inspired from visual cortex structure, where neurons are sensitive to small subregions of the input space, called receptive fields, exploiting the strong spatially local correlation present in images [35].…”

Section: Cnn Conceptsmentioning

confidence: 99%

See 3 more Smart Citations

Memristor Neural Network Design

Huang¹,

Zhang²,

Li³

et al. 2018

Memristor and Memristive Neural Networks

View full text Add to dashboard Cite

Neural network, a powerful learning model, has archived amazing results. However, the current Von Neumann computing system-based implementations of neural networks are suffering from memory wall and communication bottleneck problems ascribing to the Complementary Metal Oxide Semiconductor (CMOS) technology scaling down and communication gap. Memristor, a two terminal nanosolid state nonvolatile resistive switching, can provide energy-efficient neuromorphic computing with its synaptic behavior. Crossbar architecture can be used to perform neural computations because of its high density and parallel computation. Thus, neural networks based on memristor crossbar will perform better in real world applications. In this chapter, the design of different neural network architectures based on memristor is introduced, including spiking neural networks, multilayer neural networks, convolution neural networks, and recurrent neural networks. And the brief introduction, the architecture, the computing circuits, and the training algorithm of each kind of neural networks are presented by instances. The potential applications and the prospects of memristor-based neural network system are discussed.

show abstract

Section: Cnn Conceptsmentioning

confidence: 99%

Section: Cnn Conceptsmentioning

confidence: 99%

Section: Cnn Architecturesmentioning

confidence: 99%

Section: Cnn Conceptsmentioning

confidence: 99%

See 2 more Smart Citations

Memristor Neural Network Design

Huang¹,

Zhang²,

Li³

et al. 2018

Memristor and Memristive Neural Networks

View full text Add to dashboard Cite

show abstract

“…At present, deep learning networks are mainly Stacked AutoEncoder, Restricted Boltzmann Machine, Deep Belief Network and Convolutional Neural Network (CNN), and so on. Among them, the CNN [11][12][13][14][15] is the most significant in the image classification task.…”

Section: Introductionmentioning

confidence: 99%

High performance vegetable classification from images based on AlexNet deep learning model

Zhu

et al. 2018

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

Deep learning techniques can automatically learn features from a large number of image data set. Automatic vegetable image classification is the base of many applications. This paper proposed a high performance method for vegetable images classification based on deep learning framework. The AlexNet network model in Caffe was used to train the vegetable image data set. The vegetable image data set was obtained from ImageNet and divided into training data set and test data set. The output function of the AlexNet network adopted the Rectified Linear Units (ReLU) instead of the traditional sigmoid function and the tanh function, which can speed up the training of the deep learning network. The dropout technology was used to improve the generalization of the model. The image data extension method was used to reduce overfitting in the learning process. With AlexNet network model used for training different number of vegetable image data set, the experimental results showed that the classification accuracy decreases as the number of data set decreases. The experimental verification indicated that the accuracy rate of the deep learning method in the test data set reached as high as 92.1%, which was greatly improved compared with BP neural network (78%) and SVM classifier (80.5%) methods.

show abstract

Progress in Bioinspired Photodetectors Design for Visual Information Processing

Deng

Wang

et al. 2023

Adv Funct Materials

View full text Add to dashboard Cite

Rapid development of modern science and technology has prompted explosive growth of data volumes, especially the visual information, which brings heavy pressure on information processing and computation. The classic technical route to improve the computation power of image processing units by reducing the critical dimension of the transistors according to Moore's law gradually fails due to the physical limit of transistors’ footprint and the separated architectures. Inspired by human vision systems, retina‐like photodetectors that mimic their spatial and temporal properties have attracted widespread attention. These developed architectures enable the early data processing in‐ or near‐sensor, significantly reducing the computing power required in the back end. Herein, a comprehensive review on bioinspired photodetectors that possess the spatial and temporal properties of biological vision is provided. The properties of retina are summarized and presented first. Basic structure design and operation mechanism of those photodetectors with spatial properties of retina (including the distribution of receptive fields and the shape of the hemisphere) and temporal properties of retina (including the memory properties enabled learning and the light intensity adaptation) are reviewed thoroughly. Eventually, challenges and future perspectives are commented and provided to facilitate the rapid development of in‐ or near‐sensor computing photodetectors.

show abstract

Design of memristor-based image convolution calculation in convolutional neural network

Cited by 50 publications

References 28 publications

Memristor Neural Network Design

Memristor Neural Network Design

High performance vegetable classification from images based on AlexNet deep learning model

Progress in Bioinspired Photodetectors Design for Visual Information Processing

Contact Info

Product

Resources

About