Filament formation in lithium niobate memristors supports neuromorphic programming capability

Memristor crossbars are capable of implementing learning algorithms in a much more energy and area efficient manner compared to traditional systems. However, the programmable nature of memristor crossbars must first be explored on a smaller scale to see which memristor device structures are most suitable for applications in reconfigurable computing. In this paper, we demonstrate the programmability of memristor devices with filamentary switching based on LiNbO₃, a new resistive switching oxide. We show that a range of resistance values can be set within these memristor devices using a pulse train for programming. We also show that a neuromorphic crossbar containing eight memristors was capable of correctly implementing an OR function. This work demonstrates that lithium niobate memristors are strong candidates for use in neuromorphic computing.

     

Hybrid memristor/RTD structure-based cellular neural networks with applications in image processing

Cellular neural network (CNN) has been acted as a high-speed parallel analog signal processor gradually. However, recently, since the decrease in the size of transistor is going to approach the utmost, the transistor-based integrated circuit technology hits a bottleneck. As a result, the advantage of very large scale integration implementation of CNN becomes hard to really present, and further development of this era faces severe challenges unavoidably. In this study, two types of memristor-based cellular neural networks have been proposed. One type uses a memristor to replace the linear resistor in a conventional CNN cell circuit. And the other places a resonant tunneling diode (RTD) in this position and uses memristive synaptic connections to structure a hybrid memristor RTD CNN model. The excellent performances of the proposed CNNs are verified by conventional means of, for instance, stability analysis and efficient applications in image processing. Since both the memristor and the resonant tunneling diode are nanoscale, the size of the network circuits can be greatly reduced, and the integration density of the system will be significantly improved.     

Trends of deposition and patterning techniques of TiO2 for memristor based bio-sensing applications

Memristor is a new element that has potential in various fields such as memory, neural network, FPGA, computing and bio-sensing. Among listed, research on memristor in bio-sensing applications is very minimal. There are a lot of researches done in bio-sensing applications but they are not looking at the memristive behavior effect but most of them are looking at surface effect or cyclic voltammetry effect or amperometric response. This study will focused on memristive behavior of memristor sensor in bio-sensing applications. At first, this paper discusses brief overview about deposition techniques of TiO₂. In second part, the details overview of TiO₂ patterning techniques will be covered. There are four patterning techniques that can be used for TiO₂ patterning which are lift off techniques, sol–gel base imprint lithography techniques, etching techniques and site-selective deposition techniques. Third part discussed in general about bio-sensing applications including two researches on memristor sensor that has been done. At last, this paper will propose a design of memristor sensor using TiO₂ material to be used in bio-sensing applications. TiO₂ material was chosen as the sensing material due to its wide used in sensing applications including gas sensing, bio-sensing and humidity sensing. TiO₂ is also the best material that has the best memristive behavior beside Si, ZnO and others.     

基于多层忆阻脉冲神经网络的强化学习及应用

人工神经网络（Artificial neural networks,ANNs）与强化学习算法的结合显著增强了智能体的学习能力和效率.然而,这些算法需要消耗大量的计算资源,且难以硬件实现.而脉冲神经网络（Spiking neural networks,SNNs）使用脉冲信号来传递信息,具有能量效率高、仿生特性强等特点,且有利于进一步实现强化学习的硬件加速,增强嵌入式智能体的自主学习能力.不过,目前脉冲神经网络的学习和训练过程较为复杂,网络设计和实现方面存在较大挑战.本文通过引入人工突触的理想实现元件——忆阻器,提出了一种硬件友好的基于多层忆阻脉冲神经网络的强化学习算法.特别地,设计了用于数据——脉冲转换的脉冲神经元;通过改进脉冲时间依赖可塑性（Spiking-timing dependent plasticity,STDP）规则,使脉冲神经网络与强化学习算法有机结合,并设计了对应的忆阻神经突触;构建了可动态调整的网络结构,以提高网络的学习效率;最后,以Open AI Gym中的CartPole-v0（倒立摆）和MountainCar-v0（小车爬坡）为例,通过实验仿真和对比分析,验证了方案的有效性和相对于传统强化学习方法的优势.     

An automatic feature generation approach to multiple instance learning and its applications to image databases

Automatic content-based image categorization is a challenging research topic and has many practical applications. Images are usually represented as bags of feature vectors, and the categorization problem is studied in the Multiple-Instance Learning (MIL) framework. In this paper, we propose a novel learning technique which transforms the MIL problem into a standard supervised learning problem by defining a feature vector for each image bag. Specifically, the feature vectors of the image bags are grouped into clusters and each cluster is given a label. Using these labels, each instance of an image bag can be replaced by a corresponding label to obtain a bag of cluster labels. Data mining can then be employed to uncover common label patterns for each image category. These label patterns are converted into bags of feature vectors; and they are used to transform each image bag in the data set into a feature vector such that each vector element is the distance of the image bag to a distinct pattern bag. With this new image representation, standard supervised learning algorithms can be applied to classify the images into the pre-defined categories. Our experimental results demonstrate the superiority of the proposed technique in categorization accuracy as compared to state-of-the-art methods.     

Expanded HP memristor model and simulation in STDP learning

Based on the classical HP memristor found by HP Lab, this paper presents an expanded model that making fully consideration of the influence of R _on, that is, R _on is the similar order of magnitude of R _off. Simulations proved that in some particular conditions, the hysteresis effect of the expanded model is the same as HP memristor. A comparison was made between these two models under some given conditions. Then, we built several simulations to test the classical characteristics of the expanded HP memristor. Simulation results demonstrate that the expanded model is superior to the original in some aspects like easy switching and power saving. At last, we applied the expanded HP memristor in STDP learning simulation, which shows it is a good candidate for neural network when a threshold voltage function is proposed.     

Memristive crossbar array with applications in image processing

A memristor is a kind of nonlinear resistor with memory capacity.Its resistance changes with the amount of charge or flux passing through it.As the fourth fundamental circuit element,it has huge potential applications in many fields,and has been expected to drive a revolution in circuit theory.Through numerical simulations and circuitry modeling,the basic theory and properties of memristors are analyzed,and a memristor-based crossbar array is then proposed.The array can realize storage and output for binary,grayscale and color images.A series of computer simulations demonstrates the effectiveness of the proposed scheme.Owing to the advantage of the memristive crossbar array in parallel information processing,the proposed method is expected to be used in high-speed image processing.     

Low power and high-speed FPGA implementation for 4D memristor chaotic system for image encryption

In this paper, we proposed a novel low power and high-speed FPGA implementation of the 4D memristor chaotic system with cubic nonlinearity based on Xilinx System Generator (XSG) model. Firstly, a pseudo-random number generator based on the proposed XSG FPGA implementation of the proposed 4D memristor chaotic system which implemented into Xilinx Spartan-6 X6SLX45 board with 32 fixed-point format. The aim of the FPGA implementation is increasing the frequency of the memristor chaotic random number generators. The FPGA implementation of the memristor chaotic system results show that the new design approach achieves a maximum frequency of 393 MHz and dissipates 117 m watt. The standard fifteen randomization tests are used to measure the quality of the proposed pseudo-random number generator based on the 4D memristor chaotic system and it gives an excellent randomization analysis. Also, the gray image encryption scheme based on the 4D memristor chaotic system has been introduced. The proposed cryptosystem has a large keyspace, very low correlation values, high entropy which is much closer to the ideal entropy value, a high number of pixels change rate and high unified average changing intensity values. The results and security analysis of the proposed encryption scheme demonstrate that the investigated encryption approach can protect high speed and high security against various attack.

     

Non-Gaussian Data Clustering via Expectation Propagation Learning of Finite Dirichlet Mixture Models and Applications

Learning appropriate statistical models is a fundamental data analysis task which has been the topic of continuing interest. Recently, finite Dirichlet mixture models have proved to be an effective and flexible model learning technique in several machine learning and data mining applications. In this article, the problem of learning and selecting finite Dirichlet mixture models is addressed using an expectation propagation (EP) inference framework. Within the proposed EP learning method, for finite mixture models, all the involved parameters and the model complexity (i.e. the number of mixture components), can be evaluated simultaneously in a single optimization framework. Extensive simulations using synthetic data along with two challenging real-world applications involving automatic image annotation and human action videos categorization demonstrate that our approach is able to achieve better results than comparable techniques.     

Analog memristive memory with applications in audio signal processing

Since the development of the HP memristor, much attention has been paid to studies of memris- tive devices and applications, particularly memristor-based nonvolatile semiconductor memory. Owing to its unique properties, theoretically, one could restart a memristor-based computer immediately without the need for reloading the data. Further, current memories are mainly binary and can store only ones and zeros, whereas memristors have multilevel states, which means a single memristor unit can replace many binary transistors and realize higher-density memory. It is believed that memristors can also implement analog storage besides binary and multilevel information memory. In this paper, an implementation scheme for analog memristive memory is considered. A charge-controlled memristor model is derived and the corresponding SPICE model is constructed. Special write and read operations are demonstrated through numerical analysis and circuit simulations. In addition, an audio analog record/play system using a memristor crossbar array is designed. This system can provide great storage capacity （long recording time） and high audio quality with a simple small circuit structure. A series of computer simulations and analyses verify the effectiveness of the proposed scheme.     

基于全卷积网络的图像语义分割方法综述

自全卷积网络(Fully Convolutional Network,FCN)提出以后,应用深度学习技术在图像语义分割领域受到了许多计算机视觉和机器学习研究者的关注,现在这一方向已经成为人工智能方向的研究热点.FCN的核心思想是搭建一个全卷积网络,输入任意尺寸的图像,经过模型的有效学习和推理得到相同尺寸的输出.FCN的提出给图像语义分割领域提供了新的思路,但也存在很多的缺点,比如特征分辨率低、对象存在多尺度问题等.随着研究者不断的钻研,卷积神经网络在图像分割领域逐渐得到了优化和拓展,基于FCN的主流分割框架也层出不穷.图像语义分割对于场景理解的重要性日渐突出,被广泛应用到无人驾驶技术、无人机领域和医疗影像检测与分析等任务中.因此,对图像语义分割领域的研究将值得深入研究,使其能够更好在实际应用中大放异彩.     

Flexible memristor based neuromorphic system for implementing multi-layer neural network algorithms

Abstract

This paper describes a memristor-based neuromorphic system that can be used for ex situ training of various multi-layer neural network algorithms. This system is based on an analogue neuron circuit that is capable of performing an accurate dot product calculation. The presented ex situ programming technique can be used to map many key neural algorithms directly onto the grid of resistances in a memristor crossbar. Using this weight-to-crossbar mapping approach along with the memristor based circuit architecture, complex neural algorithms can be easily implemented using this system. Some existing memristor based circuits provide an approximated dot product based on conductance summation, but neuron outputs are not directly correlated to the numerical values obtained in a traditional software approach. To show the effectiveness and versatility of this circuit, two different powerful neural networks were simulated. These include a Restricted Boltzmann Machine for character recognition and a Multilayer Perceptron trained to perform Sobel edge detection. Following these simulations, an analysis was presented that shows how both memristor accuracy and neuron circuit gain relates to output error.     

A Survey of Image Synthesis Methods for Visual Machine Learning

Image synthesis designed for machine learning applications provides the means to efficiently generate large quantities of training data while controlling the generation process to provide the best distribution and content variety. With the demands of deep learning applications, synthetic data have the potential of becoming a vital component in the training pipeline. Over the last decade, a wide variety of training data generation methods has been demonstrated. The potential of future development calls to bring these together for comparison and categorization. This survey provides a comprehensive list of the existing image synthesis methods for visual machine learning. These are categorized in the context of image generation, using a taxonomy based on modelling and rendering, while a classification is also made concerning the computer vision applications they are used. We focus on the computer graphics aspects of the methods, to promote future image generation for machine learning. Finally, each method is assessed in terms of quality and reported performance, providing a hint on its expected learning potential. The report serves as a comprehensive reference, targeting both groups of the applications and data development sides. A list of all methods and papers reviewed herein can be found at https://computergraphics.on.liu.se/image_synthesis_methods_for_visual_machine_learning/ .     

Enhancing image processing architecture using deep learning for embedded vision systems

In recent years, the success and capabilities of embedded vision have showed up in embedded applications. The embedding of vision into electronic devices such as embedded medical applications is being driven by the availability of high-performance processors, integrating with deep learning algorithms, as well as advances in image processing technology. But, including image processing in embedded vision systems need huge amount of computational capabilities even to process a single image to detect an object and it's extremely challenging to implement in embedded systems. Implementing deep learning algorithms and testing it on a task specific data set could provide enhanced results. In this paper, an approach for enhancing image processing architecture using deep learning for embedded vision systems is proposed and analyzed. Implementing deep learning algorithms and testing it on embedded vision yielded effective results.     

基于Temporal rule的忆阻神经网络电路

忆阻器是一种动态特性的电阻,其阻值可以根据外场的变化而变化,并且在外场撤掉后能够保持原来的阻值,具有类似于生物神经突触连接强度的特性,可以用来存储突触权值。在此基础上,为了实现基于Temporal rule对IRIS数据集识别学习的功能,建立了以桥式忆阻器为突触的神经网络SPICE仿真电路。采用单个脉冲的编码方式,脉冲的时刻代表着数据信息,该神经网络电路由48个脉冲输入端口、144个突触、3个输出端口组成。基于Temporal rule学习规则对突触的权值修改,通过仿真该神经网络电路对IRIS数据集的分类正确率最高能达到93.33%,表明了此神经系统结构设计在类脑脉冲神经网络中的可用性。     

基于改进忆阻器的高通滤波器设计与仿真

针对传统的忆阻器模型存在不能很好地与HP实验室提出的忆阻器物理模型中忆阻器的阻值变化特点相符的问题,提出了一种改进的带有阈值电压的忆阻器模型,该模型能很好地模拟忆阻器的"激活"现象,其特性与HP实验室的忆阻器物理模型相符;基于该改进模型设计了一种高通滤波器电路,该电路通过改变忆阻器阻值控制电路的输出信号来改变忆阻器的阻值,从而实现了滤波器截止频率的调节。SPICE仿真结果验证了设计的正确性。     

Toward Fine-grained Image Retrieval with Adaptive Deep Learning for Cultural Heritage Image

Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scales. A cultural heritage image is one of the fine-grained images because each image has the same similarity in most cases. Using the classification technique, distinguishing cultural heritage architecture may be difficult. This study proposes a cultural heritage content retrieval method using adaptive deep learning for fine-grained image retrieval. The key contribution of this research was the creation of a retrieval model that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing the old categorization of a cultural heritage image. The goal of the proposed method is to perform a retrieval task for classes. Incremental learning for new classes was conducted to reduce the re-training process. In this step, the original class is not necessary for re-training which we call an adaptive deep learning technique. Cultural heritage in the case of Thai archaeological site architecture was retrieved through machine learning and image processing. We analyze the experimental results of incremental learning for fine-grained images with images of Thai archaeological site architecture from world heritage provinces in Thailand, which have a similar architecture. Using a fine-grained image retrieval technique for this group of cultural heritage images in a database can solve the problem of a high degree of similarity among categories and a high degree of dissimilarity for a specific category. The proposed method for retrieving the correct image from a database can deliver an average accuracy of 85 percent. Adaptive deep learning for fine-grained image retrieval was used to retrieve cultural heritage content, and it outperformed state-of-the-art methods in fine-grained image retrieval.     

一种基于学习的自动图像配准检验方法

图像配准是众多具体应用的共性核心技术, 如图像融合, 变化检测等. 然而, 当参考图像经过变换后, 如何自动地确定变换后的图像是否与目标图像真正达到了配准仍然是目前文献中一个尚未很好解决的问题. 究其原因, 主要是很难找到一种图像相似性的度量方法来有效地对配准后的图像进行评价. 不同于传统的方法, 本文提出了一种基于学习的相似性度量方法, 即将图像配准的度量问题转化为模式分类问题, 由基于机器学习设计的分类器自动检验图像是否配准. 本文对 400 组图像进行了配准检验, 实验结果显示了该方法的可行性和可靠性. 尽管本文方法的具体实现是针对基于 Fourier-Mellin 变换的配准算法, 但这种基于学习的图像配准检验思想同样可以应用到其他配准方法中.     

Unsupervised Dense Light Field Reconstruction with Occlusion Awareness

Light field (LF) reconstruction is a fundamental technique in light field imaging and has applications in both software and hardware aspects. This paper presents an unsupervised learning method for LF‐oriented view synthesis, which provides a simple solution for generating quality light fields from a sparse set of views. The method is built on disparity estimation and image warping. Specifically, we first use per‐view disparity as a geometry proxy to warp input views to novel views. Then we compensate the occlusion with a network by a forward‐backward warping process. Cycle‐consistency between different views are explored to enable unsupervised learning and accurate synthesis. The method overcomes the drawbacks of fully supervised learning methods that require large labeled training dataset and epipolar plane image based interpolation methods that do not make full use of geometry consistency in LFs. Experimental results demonstrate that the proposed method can generate high quality views for LF, which outperforms unsupervised approaches and is comparable to fully‐supervised approaches.