A low-order model of biological neural networks

A biologically plausible low-order model (LOM) of biological neural networks is proposed. LOM is a recurrent hierarchical network of models of dendritic nodes and trees; spiking and nonspiking neurons; unsupervised, supervised covariance and accumulative learning mechanisms; feedback connections; and a scheme for maximal generalization. These component models are motivated and necessitated by making LOM learn and retrieve easily without differentiation, optimization, or iteration, and cluster, detect, and recognize multiple and hierarchical corrupted, distorted, and occluded temporal and spatial patterns. Four models of dendritic nodes are given that are all described as a hyperbolic polynomial that acts like an exclusive-OR logic gate when the model dendritic nodes input two binary digits. A model dendritic encoder that is a network of model dendritic nodes encodes its inputs such that the resultant codes have an orthogonality property. Such codes are stored in synapses by unsupervised covariance learning, supervised covariance learning, or unsupervised accumulative learning, depending on the type of postsynaptic neuron. A masking matrix for a dendritic tree, whose upper part comprises model dendritic encoders, enables maximal generalization on corrupted, distorted, and occluded data. It is a mathematical organization and idealization of dendritic trees with overlapped and nested input vectors. A model nonspiking neuron transmits inhibitory graded signals to modulate its neighboring model spiking neurons. Model spiking neurons evaluate the subjective probability distribution (SPD) of the labels of the inputs to model dendritic encoders and generate spike trains with such SPDs as firing rates. Feedback connections from the same or higher layers with different numbers of unit-delay devices reflect different signal traveling times, enabling LOM to fully utilize temporally and spatially associated information. Biological plausibility of the component models is discussed. Numerical examples are given to demonstrate how LOM operates in retrieving, generalizing, and unsupervised and supervised learning.     

脉冲神经网络:模型、学习算法与应用

脉冲神经网络是目前最具有生物解释性的人工神经网络,是类脑智能领域的核心组成部分.首先介绍各类常用的脉冲神经元模型以及前馈和循环型脉冲神经网络结构;然后介绍脉冲神经网络的时间编码方式,在此基础上,系统地介绍脉冲神经网络的学习算法,包括无监督学习和监督学习算法,其中监督学习算法按照梯度下降算法、结合STDP规则的算法和基于脉冲序列卷积核的算法3大类别分别展开详细介绍和总结;接着列举脉冲神经网络在控制领域、模式识别领域和类脑智能研究领域的应用,并在此基础上介绍各国脑计划中,脉冲神经网络与神经形态处理器相结合的案例;最后分析脉冲神经网络目前所存在的困难和挑战.     

一类反馈过程神经元网络模型及学习算法研究

提出了一种带有反馈输入的过程式神经元网络模型,模型为三层结构,其隐层和输出层均为过程神经元。输入层完成连续信号的输入,隐层完成输入信号的空间聚合和向输出层逐点映射,并将输出信号逐点反馈到输入层;输出层完成隐层输出信号的时、空聚合运算和系统输出。在对权函数实施正交基展开的基础上给出了该模型的学习算法。仿真实验证明了该模型的有效性和可行性。     

脉冲神经元脉冲序列学习方法综述

脉冲神经元是一种新颖的人工神经元模型,其有监督学习的目的是通过学习使得神经元激发出一串通过精确时间编码来表达特定信息的脉冲序列,故称为脉冲序列学习。针对单神经元的脉冲序列学习应用价值显著、理论基础多样、影响因素众多的特点,对已有脉冲序列学习方法进行了综述对比。首先介绍了脉冲神经元模型与脉冲序列学习的基本概念;然后详细介绍了典型的脉冲序列学习方法,指出了每种方法的理论基础和突触权值调整方式;最后通过实验比较了这些学习方法的性能,系统总结了每种方法的特点,并且讨论了脉冲序列学习的研究现状和进一步的发展方向。该研究结果有助于脉冲序列学习方法的综合应用。     

复杂工业过程的遗传模糊神经网络控制

本文提出一种基于遗传算法和监督学习方法的有效模糊神经网络控制，这种控制器采用并行处理的推理网络，具有两个重要特点：自适应和学习性，所提方法经过仿真和温控验证表明控制性能良好。     

面向图像识别的多层脉冲神经网络学习算法综述

相较于第1代和第2代神经网络,第3代神经网络的脉冲神经网络是一种更加接近于生物神经网络的模型,因此更具有生物可解释性和低功耗性。基于脉冲神经元模型,脉冲神经网络可以通过脉冲信号的形式模拟生物信号在神经网络中的传播,通过脉冲神经元的膜电位变化来发放脉冲序列,脉冲序列通过时空联合表达不仅传递了空间信息还传递了时间信息。当前面向模式识别任务的脉冲神经网络模型性能还不及深度学习,其中一个重要原因在于脉冲神经网络的学习方法不成熟,深度学习中神经网络的人工神经元是基于实数形式的输出,这使得其可以使用全局性的反向传播算法对深度神经网络的参数进行训练,脉冲序列是二值性的离散输出,这直接导致对脉冲神经网络的训练存在一定困难,如何对脉冲神经网络进行高效训练是一个具有挑战的研究问题。本文首先总结了脉冲神经网络研究领域中的相关学习算法,然后对其中主要的方法:直接监督学习、无监督学习的算法以及ANN2SNN的转换算法进行分析介绍,并对其中代表性的工作进行对比分析,最后基于对当前主流方法的总结,对未来更高效、更仿生的脉冲神经网络参数学习方法进行展望。     

The bridge relating process neural networks and traditional neural networks

The process neural network (PrNN) is an ANN model suited for solving the learning problems with signal inputs, whose elementary unit is the process neuron (PN), an emerging neuron model. There is an essential difference between the process neuron and traditional neurons, but there also exists a relation between them. The former can be approximated by the latter within any precision. First, the PN model and some PrNNs are introduced in brief. And then, two PN approximating theorems are presented and proved in detail. Each theorem gives an approximating model to the PN model, i.e., the time-domain feature expansion model and the orthogonal decomposition feature expansion model. Some corollaries are given for the PrNNs based on these two theorems. Thereafter, simulation studies are performed on some simulated signal sets and a real dataset. The results show that the PrNN can effectively suppress noises polluting the signals and generalize quite well. Finally some problems on PrNNs are discussed and further research directions are suggested.     

Higher-Order-Statistics-Based Radial Basis Function Networks for Signal Enhancement

In this paper, a higher-order-statistics (HOS)-based radial basis function (RBF) network for signal enhancement is introduced. In the proposed scheme, higher order cumulants of the reference signal were used as the input of HOS-based RBF. An HOS-based supervised learning algorithm, with mean square error obtained from higher order cumulants of the desired input and the system output as the learning criterion, was used to adapt weights. The motivation is that the HOS can effectively suppress Gaussian and symmetrically distributed non-Gaussian noise. The influence of a Gaussian noise on the input of HOS-based RBF and the HOS-based learning algorithm can be mitigated. Simulated results indicate that HOS-based RBF can provide better performance for signal enhancement under different noise levels, and its performance is insensitive to the selection of learning rates. Moreover, the efficiency of HOS-based RBF under the nonstationary Gaussian noise is stable     

基于电阻炉的单神经元PID控制器的设计及仿真

对传统电阻炉PID控制器的不足之处进行了分析,阐述了单神经元PID控制算法的优点。介绍了根据有监督hebb学习算法,再结合实际控制经验而设计的单神经元控制器。分析了单神经元控制器中各个参数的意义与取值原则,并用Matlab软件对单神经元控制器在阶跃输入信号的情况下进行了仿真。仿真内容有:连接权值、K值变化对系统的影响及选取方法;单神经元PID控制器与常规PID控制器的抗干扰能力和调节性能对比。仿真结果证明单神经元控制器具有很好的参数自整定能力,且抗干扰能力强,超调量小,控制效果在各个方面都要优于常规PID控制器,单神经元控制器用于电阻炉温度控制系统比传统的PID控制器能取得更好的控制效果。     

仿生型脉冲神经网络学习算法和网络模型

为解决脉冲神经网络训练困难的问题,基于仿生学思路,提出脉冲神经网络的权值学习算法和结构学习算法,设计一种含有卷积结构的脉冲神经网络模型,搭建适合脉冲神经网络的软件仿真平台。实验结果表明,权值学习算法训练的网络对MNIST数据集识别准确率能够达到84.12%,具备良好的快速收敛能力和低功耗特点;结构学习算法能够自动生成网络结构,具有高度生物相似性。     

Unsupervised query-based learning of neural networks usingselective-attention and self-regulation

Query-based learning (QBL) has been introduced for training a supervised network model with additional queried samples. Experiments demonstrated that the classification accuracy is further increased. Although QBL has been successfully applied to supervised neural networks, it is not suitable for unsupervised learning models without external supervisors. In this paper, an unsupervised QBL (UQBL) algorithm using selective-attention and self-regulation is proposed. Applying the selective-attention, we can ask the network to respond to its goal-directed behavior with self-focus. Since there is no supervisor to verify the self-focus, a compromise is then made to environment-focus with self-regulation. In this paper, we introduce UQBL1 and UQBL2 as two versions of UQBL; both of them can provide fast convergence. Our experiments indicate that the proposed methods are more insensitive to network initialization. They have better generalization performance and can be a significant reduction in their training size.     

The influence of the radial basis function training strategy on the performance of a neural gripper

In this article, a neural network-based grasping system that is able to collect objects of arbitrary shape is introduced. The grasping process is split into three functional blocks: image acquisition and processing, contact point estimation, and contact force determination. The paper focuses on the second block, which contains two neural networks. A competitive Hopfield neural network first determines an approximate polygon for an object outline. These polygon edges are the input for a supervised neural network model [radial basis function (RBF) or multilayer perceptions], which then defines the contact points. Tests were conducted with objects of different shapes, and experimental results suggest that the performance of the neural gripper and its learning rate are significantly influenced by the choice of supervised training model and RBF learning algorithm.     

ART-EMAP: A neural network architecture for object recognition byevidence accumulation

A new neural network architecture is introduced for the recognition of pattern classes after supervised and unsupervised learning. Applications include spatio-temporal image understanding and prediction and 3D object recognition from a series of ambiguous 2D views. The architecture, called ART-EMAP, achieves a synthesis of adaptive resonance theory (ART) and spatial and temporal evidence integration for dynamic predictive mapping (EMAP). ART-EMAP extends the capabilities of fuzzy ARTMAP in four incremental stages. Stage 1 introduces distributed pattern representation at a view category field. Stage 2 adds a decision criterion to the mapping between view and object categories, delaying identification of ambiguous objects when faced with a low confidence prediction. Stage 3 augments the system with a field where evidence accumulates in medium-term memory. Stage 4 adds an unsupervised learning process to fine-tune performance after the limited initial period of supervised network training. Each ART-EMAP stage is illustrated with a benchmark simulation example, using both noisy and noise-free data.     

Delay learning and polychronization for reservoir computing

We propose a multi-timescale learning rule for spiking neuron networks, in the line of the recently emerging field of reservoir computing. The reservoir is a network model of spiking neurons, with random topology and driven by STDP (spike-time-dependent plasticity), a temporal Hebbian unsupervised learning mode, biologically observed. The model is further driven by a supervised learning algorithm, based on a margin criterion, that affects the synaptic delays linking the network to the readout neurons, with classification as a goal task. The network processing and the resulting performance can be explained by the concept of polychronization, proposed by Izhikevich [Polychronization: computation with spikes, Neural Comput. 18(2) (2006) 245–282], on physiological grounds. The model emphasizes that polychronization can be used as a tool for exploiting the computational power of synaptic delays and for monitoring the topology and activity of a spiking neuron network.     

New automated learning CPG for rhythmic patterns

In this paper, we suggest a new supervised learning method called Fourier based automated learning central pattern generators (FAL-CPG), for learning rhythmic signals. The rhythmic signal is analyzed with Fourier analysis and fitted with a finite Fourier series. CPG parameters are selected by direct comparison with the Fourier series. It is shown that the desired rhythmic signal is learned and reproduced with high accuracy. The resulting CPG network offers several advantages such as, modulation and robustness against perturbation. The proposed learning method is simple, straightforward and efficient. Furthermore, it is suitable for on-line applications. The effectiveness of the proposed method is shown by comparison with four other supervised learning methods as well as an industrial robotic trajectory following application.     

A Neural Network with Evolutionary Neurons

A neural network, combining evolution and learning is introduced. The novel feature of the proposed network is the evolutionary character of its neurons. The argument of the transfer function performed by the neurons in the network is neither a linear nor polynomial function of the inputs to the neuron, but an unknown general function P(·). The adequate functional form P(·) for each neuron, is achieved during the learning period by means of genetic programming. The proposed neural network is applied to the problem domain of time series prediction of the Mackey-Glass delay differential equation. Simulation results indicate that the new neural network is effective.     

过程神经元网络的研究与进展

过程神经元网络是一种适合于处理过程式信号输入的网络,其基本单元是过程神经元--一种新的神经元模型.本文介绍了过程神经元及其网络模型的基本理论及其特点,概述了一种基于梯度下降的学习算法及算法流程,总结了近几年来过程神经元网络及其算法的最新研究进展,并给出了一些已有的应用成果,讨论了一些具有前景的研究方向.     

Supervised learning in a recurrent network of rate-model neurons exhibiting frequency adaptation

For gradient descent learning to yield connectivity consistent with real biological networks, the simulated neurons would have to include more realistic intrinsic properties such as frequency adaptation. However, gradient descent learning cannot be used straightforwardly with adapting rate-model neurons because the derivative of the activation function depends on the activation history. The objectives of this study were to (1) develop a simple computational approach to reproduce mathematical gradient descent and (2) use this computational approach to provide supervised learning in a network formed of rate-model neurons that exhibit frequency adaptation.The results of mathematical gradient descent were used as a reference in evaluating the performance of the computational approach. For this comparison, standard (nonadapting) rate-model neurons were used for both approaches. The only difference was the gradient calculation: the mathematical approach used the derivative at a point in weight space, while the computational approach used the slope for a step change in weight space. Theoretically, the results of the computational approach should match those of the mathematical approach, as the step size is reduced but floating-point accuracy formed a lower limit to usable step sizes. A systematic search for an optimal step size yielded a computational approach that faithfully reproduced the results of mathematical gradient descent.The computational approach was then used for supervised learning of both connection weights and intrinsic properties of rate-model neurons to convert a tonic input into a phasic-tonic output pattern. Learning produced biologically realistic connectivity that essentially used a monosynaptic connection from the tonic input neuron to an output neuron with strong frequency adaptation as compared to a complex network when using nonadapting neurons. Thus, more biologically realistic connectivity was achieved by implementing rate-model neurons with more realistic intrinsic properties. Our computational approach could be applied to learning of other neuron properties.     

基于卷积计算的多层脉冲神经网络的监督学习

针对脉冲神经元基于精确定时的多脉冲编码信息的特点,提出了一种基于卷积计算的多层脉冲神经网络监督学习的新算法。该算法应用核函数的卷积计算将离散的脉冲序列转换为连续函数,在多层前馈脉冲神经网络结构中,使用梯度下降的方法得到基于核函数卷积表示的学习规则,并用来调整神经元连接的突触权值。在实验部分,首先验证了该算法学习脉冲序列的效果,然后应用该算法对Iris数据集进行分类。结果显示,该算法能够实现脉冲序列复杂时空模式的学习,对非线性模式分类问题具有较高的分类正确率。     

基于单神经元的永磁同步电机解耦控制

针对永磁同步电机(PMSM)磁场定向控制为代表的传统解耦策略难以实现高性能控制的问题,本文利用神经网络不依赖对象模型的特点以及出色的学习能力,提出了一种基于单神经元的永磁同步电机解耦控制策略.在传统磁场定向控制模型的基础上,构建了基于单神经元的永磁同步电机解耦控制系统,进行了仿真,并搭建以数字信号处理器为核心的电机控制实验平台上进行实验论证.结果表明,基于单神经元解耦的永磁同步电机控制系统具有快速响应能力,并且几乎达到无静差、无超调,实现了PMSM的高性能控制.