Locally excitatory globally inhibitory oscillator networks

A novel class of locally excitatory, globally inhibitory oscillator networks (LEGION) is proposed and investigated. The model of each oscillator corresponds to a standard relaxation oscillator with two time scales. In the network, an oscillator jumping up to its active phase rapidly recruits the oscillators stimulated by the same pattern, while preventing other oscillators from jumping up. Computer simulations demonstrate that the network rapidly achieves both synchronization within blocks of oscillators that are stimulated by connected regions and desynchronization between different blocks. This model lays a physical foundation for the oscillatory correlation theory of feature binding and may provide an effective computational framework for scene segmentation and figure/ground segregation in real time.     

Motion segmentation based on motion/brightness integration andoscillatory correlation

A segmentation method based on the integration of motion and brightness is proposed for image sequences. The method is composed of two parallel pathways that process motion and brightness, respectively, Inspired by the visual system, the motion pathway has two stages. The first stage estimates local motion at locations with reliable information. The second stage performs segmentation based on local motion estimates. In the brightness pathway, the input scene is segmented into regions based on brightness distribution. Subsequently, segmentation results from the two pathways are integrated to refine motion estimates. The final segmentation is performed in the motion network based on refined estimates. For segmentation, locally excitatory globally inhibitory oscillator network (LEGION) architecture is employed whereby the oscillators corresponding to a region of similar motion/brightness oscillate in synchrony and different regions attain different phases. Results on synthetic and real image sequences are provided, and comparisons with other methods are made.     

Texture segmentation using Gaussian-Markov random fields and neuraloscillator networks

We propose an image segmentation method based on texture analysis. Our method is composed of two parts. The first part determines a novel set of texture features derived from a Gaussian-Markov random fields (GMRF) model. Unlike a GMRF-based approach, our method does not employ model parameters as features or require the extraction of features for a fixed set of texture types a priori. The second part is a 2D array of locally excitatory globally inhibitory oscillator networks (LEGION). After being filtered for noise suppression, features are used to determine the local couplings in the network. When LEGION runs, the oscillators corresponding to the same texture tend to synchronize, whereas different texture regions tend to correspond to distinct phases. In simulations, a large system of differential equations is solved for the first time using a recently proposed method for integrating relaxation oscillator networks. We provide results on real texture images to demonstrate the performance of our method.     

Synchrony and desynchrony in integrate-and-fire oscillators.

Due to many experimental reports of synchronous neural activity in the brain, there is much interest in understanding synchronization in networks of neural oscillators and its potential for computing perceptual organization. Contrary to Hopfield and Herz (1995), we find that networks of locally coupled integrate-and-fire oscillators can quickly synchronize. Furthermore, we examine the time needed to synchronize such networks. We observe that these networks synchronize at times proportional to the logarithm of their size, and we give the parameters used to control the rate of synchronization. Inspired by locally excitatory globally inhibitory oscillator network (LEGION) dynamics with relaxation oscillators (Terman & Wang, 1995), we find that global inhibition can play a similar role of desynchronization in a network of integrate-and-fire oscillators. We illustrate that a LEGION architecture with integrate-and-fire oscillators can be similarly used to address image analysis.     

On connectedness: a solution based on oscillatory correlation

A long-standing problem in Neural Comp has been the problem of connectedness, first identified by Minsky and Papert (1969). This problem served as the cornerstone for them to establish analytically that perceptrons are fundamentally limited in computing geometrical (topological) properties. A solution to this problem is offered by a different class of neural networks: oscillator networks. To solve the problem, the representation of oscillatory correlation is employed, whereby one pattern is represented as a synchronized block of oscillators and different patterns are represented by distinct blocks that desynchronize from each other. Oscillatory correlation emerges from LEGION (locally excitatory globally inhibitory oscillator network), whose architecture consists of local excitation and global inhibition among neural oscillators. It is further shown that these oscillator networks exhibit sensitivity to topological structure, which may lay a neurocomputational foundation for explaining the psychophysical phenomenon of topological perception.     

Synchronization and desynchronization in a network of locallycoupled Wilson-Cowan oscillators

A network of Wilson-Cowan (WC) oscillators is constructed, and its emergent properties of synchronization and desynchronization are investigated by both computer simulation and formal analysis. The network is a 2D matrix, where each oscillator is coupled only to its neighbors. We show analytically that a chain of locally coupled oscillators (the piecewise linear approximation to the WC oscillator) synchronizes, and we present a technique to rapidly entrain finite numbers of oscillators. The coupling strengths change on a fast time scale based on a Hebbian rule. A global separator is introduced which receives input from and sends feedback to each oscillator in the matrix. The global separator is used to desynchronize different oscillator groups. Unlike many other models, the properties of this network emerge from local connections that preserve spatial relationships among components and are critical for encoding Gestalt principles of feature grouping. The ability to synchronize and desynchronize oscillator groups within this network offers a promising approach for pattern segmentation and figure/ground segregation based on oscillatory correlation.     

Weight adaptation and oscillatory correlation for imagesegmentation

We propose a method for image segmentation based on a neural oscillator network. Unlike previous methods, weight adaptation is adopted during segmentation to remove noise and preserve significant discontinuities in an image. Moreover, a logarithmic grouping rule is proposed to facilitate grouping of oscillators representing pixels with coherent properties. We show that weight adaptation plays the roles of noise removal and feature preservation. In particular, our weight adaptation scheme is insensitive to termination time and the resulting dynamic weights in a wide range of iterations lead to the same segmentation results. A computer algorithm derived from oscillatory dynamics is applied to synthetic and real images, and simulation results show that the algorithm yields favorable segmentation results in comparison with other recent algorithms. In addition, the weight adaptation scheme can be directly transformed to a novel feature-preserving smoothing procedure. We also demonstrate that our nonlinear smoothing algorithm achieves good results for various kinds of images.     

Scene analysis by integrating primitive segmentation andassociative memory

Scene analysis is a major aspect of perception and continues to challenge machine perception. This paper addresses the scene-analysis problem by integrating a primitive segmentation stage with a model of associative memory. The model is a multistage system that consists of an initial primitive segmentation stage, a multimodule associative memory, and a short-term memory (STM) layer. Primitive segmentation is performed by a locally excitatory globally inhibitory oscillator network (LEGION), which segments the input scene into multiple parts that correspond to groups of synchronous oscillations. Each segment triggers memory recall and multiple recalled patterns then interact with one another in the STM layer. The STM layer projects to the LEGION network, giving rise to memory-based grouping and segmentation. The system achieves scene analysis entirely in phase space, which provides a unifying mechanism for both bottom-up analysis and top-down analysis. The model is evaluated with a systematic set of three-dimensional (3-D) line drawing objects, which are arranged in an arbitrary fashion to compose input scenes that allow object occlusion. Memory-based organization is responsible for a significant improvement in performance. A number of issues are discussed, including input-anchored alignment, top-down organization, and the role of STM in producing context sensitivity of memory recall.     

Synchronization in Time-delayed Binary Oscillatory Network

We introduce a network of binary oscillators coupled with time delays. Based on the investigation of the dynamics of single time-delayed binary oscillator, the behaviour of a pair of oscillators with excitatory coupling is analyzed in detail. It is shown that perfect synchronous solutions exist for a wide range of initial conditions in the presented oscillatory network.     

Recurrent network with large representational capacity

A recurrent network is proposed with the ability to bind image features into a unified surface representation within a single layer and without capacity limitations or border effects. A group of cells belonging to the same object or surface is labeled with the same activity amplitude, while cells in different groups are kept segregated due to lateral inhibition. Labeling is achieved by activity spreading through local excitatory connections. In order to prevent uncontrolled spreading, a separate network computes the intensity difference between neighboring locations and signals the presence of the surface boundary, which constrains local excitation. The quality of surface representation is not compromised due to the self-excitation. The model is also applied on gray-level images. In order to remove small, noisy regions, a feedforward network is proposed that computes the size of surfaces. Size estimation is based on the difference of dendritic inhibition in lateral excitatory and inhibitory pathways, which allows the network to selectively integrate signals only from cells with the same activity amplitude. When the output of the size estimation network is combined with the recurrent network, good segmentation results are obtained. Both networks are based on biophysically realistic mechanisms such as dendritic inhibition and multiplicative integration among different dendritic branches.     

多通道融合可分离卷积神经网络下的脑部磁共振图像分割

目的 卷积神经网络方法可以提取到图像的深层次信息特征,在脑部磁共振图像（MRI）分割领域展现出优秀的性能。但大部分深度学习方法都存在参数量大,边缘分割不准确的问题。为克服上述问题,本文提出一种多通道融合可分离卷积神经网络（MFSCNN）模型分割脑图像。方法 首先,在训练集中增加待分割脑结构及其边缘像素点的权重,强制使网络学习如何分割脑结构边缘部分,从而提升整体脑结构分割的准确率。其次,引入残差单元,以避免梯度弥散,同时使用深度可分离卷积代替原始的卷积层,在不改变网络每个阶段特征通道数的情况下,减少了网络训练的参数数量和训练时间,降低了训练成本。最后,将不同阶段的特征信息合并在一起,进行通道混洗,得到同时包含深浅层次信息的增强信息特征,加入到网络中进行训练,每个阶段的输入特征信息更丰富,学习特征的速度和收敛速度更快,显著地提升了网络的分割性能。结果 在IBSR（internet brain segmentation repositor）数据集上的分割结果表明,MFSCNN的分割性能相对于普通卷积神经网络（CNN）方法要明显提高,且在边缘复杂的部分,分割效果更理想,Dice和IOU（intersection over union）值分别提升了0.9% 6.6%,1.3% 9.7%。在边缘平滑的部分,MFSCNN方法比引入残差块的神经网络模型（ResCNN）和引入局部全连接模块的神经网络模型（DenseCNN）分割效果要好,而且MFSCNN的参数量仅为ResCNN的50%,DenseCNN的28%,在提升分割性能的同时,也降低了运算复杂度,缩短了训练时间。同时,在IBSR、Hammer67n20、LPBA40这3个数据集上,MFSCNN的分割性能比现有的其他主流方法更出色。结论 本文提出的MFSCNN方法,加强了网络特征的信息量,提升了网络模型的训练速度,在不同数据集上均获得更精确的MR脑部图像分割结果。     

Theoretical and evolutionary parameter tuning of neural oscillators with a double-chain structure for generating rhythmic signals

A neural oscillator with a double-chain structure is one of the central pattern generator models used to simulate and understand rhythmic movements in living organisms. However, it is difficult to reproduce desired rhythmic signals by tuning an enormous number of parameters of neural oscillators. In this study, we propose an automatic tuning method consisting of two parts. The first involves tuning rules for both the time constants and the amplitude of the oscillatory outputs based on theoretical analyses of the relationship between parameters and outputs of the neural oscillators. The second involves an evolutionary tuning method with a two-step genetic algorithm (GA), consisting of a global GA and a local GA, for tuning parameters such as neural connection weights that have no exact tuning rule. Using numerical experiments, we confirmed that the proposed tuning method could successfully tune all parameters and generate sinusoidal waves. The tuning performance of the proposed method was less affected by factors such as the number of excitatory oscillators or the desired outputs. Furthermore, the proposed method was applied to the parameter-tuning problem of some types of artificial and biological wave reproduction and yielded optimal parameter values that generated complex rhythmic signals in Caenorhabditis elegans without trial and error.     

Image segmentation by networks of spiking neurons

A network of leaky integrate-and-fire (IAF) neurons is proposed to segment gray-scale images. The network architecture with local competition between neurons that encode segment assignments of image blocks is motivated by a histogram clustering approach to image segmentation. Lateral excitatory connections between neighboring image sites yield a local smoothing of segments. The mean firing rate of class membership neurons encodes the image segmentation. A weight modification scheme is proposed that estimates segment-specific prototypical histograms. The robustness properties of the network implementation make it amenable to an analog VLSI realization. Results on synthetic and real-world images demonstrate the effectiveness of the architecture.     

残差密集空间金字塔网络的城市遥感图像分割

目的 遥感图像语义分割是根据土地覆盖类型对图像中每个像素进行分类,是遥感图像处理领域的一个重要研究方向。由于遥感图像包含的地物尺度差别大、地物边界复杂等原因,准确提取遥感图像特征具有一定难度,使得精确分割遥感图像比较困难。卷积神经网络因其自主分层提取图像特征的特点逐步成为图像处理领域的主流算法,本文将基于残差密集空间金字塔的卷积神经网络应用于城市地区遥感图像分割,以提升高分辨率城市地区遥感影像语义分割的精度。方法 模型将带孔卷积引入残差网络,代替网络中的下采样操作,在扩大特征图感受野的同时能够保持特征图尺寸不变;模型基于密集连接机制级联空间金字塔结构各分支,每个分支的输出都有更加密集的感受野信息;模型利用跳线连接跨层融合网络特征,结合网络中的高层语义特征和低层纹理特征恢复空间信息。结果 基于ISPRS （International Society for Photogrammetry and Remote Sensing） Vaihingen地区遥感数据集展开充分的实验研究,实验结果表明,本文模型在6种不同的地物分类上的平均交并比和平均F₁值分别达到69.88%和81.39%,性能在数学指标和视觉效果上均优于SegNet、pix2pix、Res-shuffling-Net以及SDFCN （symmetrical dense-shortcut fully convolutional network）算法。结论 将密集连接改进空间金字塔池化网络应用于高分辨率遥感图像语义分割,该模型利用了遥感图像不同尺度下的特征、高层语义信息和低层纹理信息,有效提升了城市地区遥感图像分割精度。     

Grouping synchronization in a pulse-coupled network of chaotic spiking oscillators

This paper studies a pulse-coupled network consisting of simple chaotic spiking oscillators (CSOs). If a unit oscillator and its neighbor(s) have (almost) the same parameter values, they exhibit in-phase synchronization of chaos. As the parameter values differ, they exhibit asynchronous phenomena. Based on such behavior, some synchronous groups appear partially in the network. Typical phenomena are verified in the laboratory via a simple test circuit. These phenomena can be evaluated numerically by using an effective mapping procedure. We then apply the proposed network to image segmentation. Using a lattice pulse-coupled network via grouping synchronous phenomena, the input image data can be segmented into some sub-regions.     

基于空间特征的谱聚类含噪图像分割

为克服传统谱聚类算法应用到含噪图像分割时易受到图像中噪声影响的问题,提出一种基于空间特征的谱聚类含噪图像分割算法。该方法利用图像各个像素的灰度信息、局部空间邻接信息及非局部空间信息设计像素的三维特征,通过引入空间紧致性函数建立像素特征点与其K个最近邻之间的相似性,进而利用谱聚类算法得到图像的最终分割结果。实验中采用含噪的人工图像、自然图像及合成孔径雷达图像与空间模糊聚类、规范切谱聚类和Nystrm方法3种算法进行对比实验,实验结果验证文中方法能克服图像中噪声影响并取得较满意的分割效果。     

Learning lateral interactions for feature binding and sensory segmentation from prototypic basis interactions

We present a hybrid learning method bridging the fields of recurrent neural networks, unsupervised Hebbian learning, vector quantization, and supervised learning to implement a sophisticated image and feature segmentation architecture. This architecture is based on the competitive layer model (CLM), a dynamic feature binding model, which is applicable on a wide range of perceptual grouping and segmentation problems. A predefined target segmentation can be achieved as attractor states of this linear threshold recurrent network, if the lateral weights are chosen by Hebbian learning. The weight matrix is given by the correlation matrix of special pattern vectors with a structure dependent on the target labeling. Generalization is achieved by applying vector quantization on pair-wise feature relations, like proximity and similarity, defined by external knowledge. We show the successful application of the method to a number of artificial test examples and a medical image segmentation problem of fluorescence microscope cell images.     

A new synaptic plasticity rule for networks of spiking neurons

In this paper, we describe a new Synaptic Plasticity Activity Rule (SAPR) developed for use in networks of spiking neurons. Such networks can be used for simulations of physiological experiments as well as for other computations like image analysis. Most synaptic plasticity rules use artificially defined functions to modify synaptic connection strengths. In contrast, our rule makes use of the existing postsynaptic potential values to compute the value of adjustment. The network of spiking neurons we consider consists of excitatory and inhibitory neurons. Each neuron is implemented as an integrate-and-fire model that accurately mimics the behavior of biological neurons. To test performance of our new plasticity rule we designed a model of a biologically-inspired signal processing system, and used it for object detection in eye images of diabetic retinopathy patients, and lung images of cystic fibrosis patients. The results show that the network detects the edges of objects within an image, essentially segmenting it. Our ultimate goal, however, is not the development of an image segmentation tool that would be more efficient than nonbiological algorithms, but developing a physiologically correct neural network model that could be applied to a wide range of neurological experiments. We decided to validate the SAPR by using it in a network of spiking neurons for image segmentation because it is easy to visually assess the results. An important thing is that image segmentation is done in an entirely unsupervised way.     

Separation of speech from interfering sounds based on oscillatorycorrelation

A multistage neural model is proposed for an auditory scene analysis task-segregating speech from interfering sound sources. The core of the model is a two-layer oscillator network that performs stream segregation on the basis of oscillatory correlation. In the oscillatory correlation framework, a stream is represented by a population of synchronized relaxation oscillators, each of which corresponds to an auditory feature, and different streams are represented by desynchronized oscillator populations. Lateral connections between oscillators encode harmonicity, and proximity in frequency and time. Prior to the oscillator network are a model of the auditory periphery and a stage in which mid-level auditory representations are formed. The model has been systematically evaluated using a corpus of voiced speech mixed with interfering sounds, and produces improvements in terms of signal-to-noise ratio for every mixture. A number of issues including biological plausibility and real-time implementation are also discussed.