近存储饱和状态下联想学习记忆的神经网络模型

本文提出了神经网络在近饱和状态下的一种联想学习记忆模型.讨论了该模型的主要特性,对由100个神经元、记忆10个随机图样组成的网络系统给出并分析了计算机模拟结果,讨论了该模型的学习律与传统的Hebb学习律的区别,研究了网络在学习记忆和联想新态时初始噪声Pi和联想噪声Pa对新态恢复行为的影响,总结了在近饱和状态下该模型所具有的优势.     

适用于鼠学习记忆行为训练的三个新模型

目的检测模拟自然生活状态下大鼠的学习记忆行为。方法：自制微机控制的多功能训练系统,设计训练模型,即指定通过、交替选择和择洞逃避。结果：三个新模型能较好地检测大鼠日常生活有关学习记忆行为。结论：模型具备客观、形象直观和省时的特点     

带有隐含神经元的单层神经网络模型

提出了一种带有隐含神经元的单层神经网络模型。把网络的记忆容量区分为信息记忆容量和物理记忆容量。新模型能记忆相关图样,其信息容量α_i(最大记忆图样数/表达神经元数)首次超过了1。所作出的计算机模拟结果,表明了理论分析的正确性,证实了由5×5个显神经元组成的点阵能记住包含26个英文字母和4个任选图样的30个图样,因此该模型为神经网络的广泛应用提供了一条重要途径。     

学习记忆小动物模型浅议

介绍了几种国内外常用的学习记忆小动物模型的操作方法，并简略介绍了一种国内未见报道的无奖惩效应的改良“十”字迷宫，该动物模型贴近动物自然本色，避免了奖惩效应对学习记忆的影响。     

具有时滞的Hopfield人工神经网络动力系统模型的全局渐近稳定性

Hopfield人工神经网络动力系统模型平衡点的全局渐近稳定性在网络记忆以及最优化等领域具有广泛的应用。本文中,作者研究了一类具有时滞的Hopfield人工神经网络动力系统,通过构造Liapunov泛函的方法,获得了其平衡点全局渐近稳定和局部渐近稳定的充分判定条件。所给出的判定条件只依赖于系统本身的拳数参数和传递函数以及系统中出现的部分时滞。同时,当系统的自身反馈项为负时,此自身反馈项对于系统的稳定性起到稳定化的作用。此外,数值模拟表明时滞的变化对于系统的稳定性具有重要的影响。可破坏系统的稳定性。进而产生周期振动或更为复杂的非线性现象。     

慢性束缚应激对SD和Wistar大鼠学习记忆能力的影响

目的探讨慢性束缚应激对Wistar、SD两种品系大鼠学习记忆能力的影响,为应激模型中实验动物的选择提供依据。方法对两种品系大鼠(Wistar、SD)采用每天束缚10 h,束缚28 d建立慢性应激模型。采用物体认知新物体识别实验和Morris水迷宫空间学习、工作记忆行为学检测方法,观察束缚应激对两种品系实验动物学习记忆能力的影响。结果束缚28 d后,物体识别实验中,Wistar、SD模型组的辨别指数(discrimination index,DI)均低于对照组,但只有SD两组间差异存在显著性(P0.05);水迷宫空间学习阶段,SD模型组潜伏期高于对照组,第5天差异有显著性(P0.05),而Wistar模型组与对照组间的潜伏期没有差异;水迷宫工作记忆阶段,SD大鼠模型组与正常组比较,潜伏期显著增加(P0.05),Wistar模型大鼠的潜伏期与对照组比较没有显著差异。结论新物体识别实验和水迷宫实验,这两种反应动物不同学习记忆能力的行为学实验结果都表明,慢性束缚应激(10 h,28 d)对SD大鼠学习记忆能力的损伤较Wistar大鼠明显。SD大鼠可能更适合作为慢性应激所致学习记忆损伤动物模型。     

表观遗传修饰在学习记忆中的研究进展

学习记忆是大脑的重要功能.记忆的形成涉及基因转录、新蛋白质合成和突触可塑性改变等一系列分子和细胞乃至神经环路的变化.近些年研究者逐渐发现各种表观遗传修饰,包括DNA甲基化、组蛋白修饰及RNA修饰在各种学习记忆类型、记忆阶段和突触可塑性中发挥了不同程度的作用.本文阐述了参与学习记忆的不同表观遗传调控因子,为进一步理解学习记忆的机制提供一定的理论依据.     

记忆T细胞平行分化模型的理论研究

为了从理论上讨论T细胞记忆维持机制的问题,基于T细胞的平行分化假说建立了非线性理论模型,利用此模型,在不同的抗原初值下得到了三种不同类型的应答。用优化剂量的抗原免疫生物体并且抗原存在时记忆能持续很长的时间,而失去抗原的同时将失去记忆,得出记忆T细胞平行分化模型确有记忆机制;并发现记忆强度与剩余抗原量有直接的关系,还进一步讨论了记忆细胞寿命的问题,并对体外情况作了预言。     

一门真正的交叉科学

神经系统(脑)信息处理的研究,引起了一些著名物理学家的兴趣。分子生物学的奠基者,DNA双螺旋结构的提出者之一,F.H.Crick,现转向搞脑科学,特别对视觉信息加工问题潜心研究,已作出了一些工作。1972年诺贝尔物理学奖获得者,超导理论家L.N.Co-oper,现在对记忆问题很有兴趣,提出了一个关于记忆的模型。美国物理学家John Hopfield曾提出一个可以实现联想记忆等脑功能的神经网络数学模型,已由美国两家公司制成硬件,对智能计算机的实现将是一     

蜜蜂的识别与记忆

本文概述了蜜蜂在识别过程中与学习行为有关的记忆特性。蜜蜂具有四种类型的记忆,即工作记忆,早期记忆,晚期记忆和永久记忆;关于蜜蜂记忆的方式主要有两种不同的假设,一种认为是按图形的方式记忆的,另一种认为是按参数的方式记忆的。文中介绍了蜜蜂对于位置记忆,花形状记忆和路标记忆有关的行为实验及其模型方面的研究进展。     

Efficient and robust associative memory from a generalized Bloom filter

We develop a variant of a Bloom filter that is robust to hardware failure and show how it can be used as an efficient associative memory. We define a measure of the information recall and show that our new associative memory is able to recall more than twice as much information as a Hopfield network. The extra efficiency of our associative memory is all the more remarkable as it uses only bits while the Hopfield network uses integers.     

On the behavior of some associative neural networks

Since Hopfield published his work on an associative memory model, a large number of works have studied the model from several angles and showed in particular its weaknesses, and presented ways to overcome them. Most of the proposed solutions seem to us however not biologically plausible. In this paper we present a simple statistical analysis of two networks similar to the Hopfield net, and show that the usage of positive feedback enhances the net recognizing capability without jeopardizing the stability. We also describe a layered parallel network composed of modules, each module being a modified Hopfield net. We finally present computer simulation results to support our analytical findings. The most important principles of this network are supported by data from the world of neurobiology.     

Recognition of general patterns using neural networks

The Hopfield model of neural network stores memory in its symmetric synaptic connections and can only learn to recognize sets of nearly orthogonal patterns. A new algorithm is put forth to permit the recognition of general (non-orthogonal) patterns. The algorithm specifies the construction of the new network's memory matrix T _ij, which is, in general, asymmetrical and contains the Hopfield neural network (Hopfield 1982) as a special case. We find further that in addition to this new algorithm for general pattern recognition, there exists in fact a large class of T _ij memory matrices which permit the recognition of non-orthogonal patterns. The general form of this class of T _ij memory matrix is presented, and the projection matrix neural network (Personnaz et al. 1985) is found as a special case of this general form. This general form of memory matrix extends the library of memory matrices which allow a neural network to recognize non-orthogonal patterns. A neural network which followed this general form of memory matrix was modeled on a computer and successfully recognized a set of non-orthogonal patterns. The new network also showed a tolerance for altered and incomplete data. Through this new method, general patterns may be taught to the neural network.     

A new neural network architecture with associative memory, pruning and order-sensitive learning

A new paradigm of neural network architecture is proposed that works as associative memory along with capabilities of pruning and order-sensitive learning. The network has a composite structure wherein each node of the network is a Hopfield network by itself. The Hopfield network employs an order-sensitive learning technique and converges to user-specified stable states without having any spurious states. This is based on geometrical structure of the network and of the energy function. The network is so designed that it allows pruning in binary order as it progressively carries out associative memory retrieval. The capacity of the network is 2n, where n is the number of basic nodes in the network. The capabilities of the network are demonstrated by experimenting on three different application areas, namely a Library Database, a Protein Structure Database and Natural Language Understanding.     

Molecular associative memory

An example of a kinetic system with address-bearing molecules and directed interactions is investigated. We show that by introducing exchange between Ising spins via the address-bearing messengers, the Hopfield model of associative memory can be made local.     

Flexible Kernel Memory

This paper introduces a new model of associative memory, capable of both binary and continuous-valued inputs. Based on kernel theory, the memory model is on one hand a generalization of Radial Basis Function networks and, on the other, is in feature space, analogous to a Hopfield network. Attractors can be added, deleted, and updated on-line simply, without harming existing memories, and the number of attractors is independent of input dimension. Input vectors do not have to adhere to a fixed or bounded dimensionality; they can increase and decrease it without relearning previous memories. A memory consolidation process enables the network to generalize concepts and form clusters of input data, which outperforms many unsupervised clustering techniques; this process is demonstrated on handwritten digits from MNIST. Another process, reminiscent of memory reconsolidation is introduced, in which existing memories are refreshed and tuned with new inputs; this process is demonstrated on series of morphed faces.     

Optimal path-finding through mental exploration based on neural energy field gradients

Rodent animal can accomplish self-locating and path-finding task by forming a cognitive map in the hippocampus representing the environment. In the classical model of the cognitive map, the system (artificial animal) needs large amounts of physical exploration to study spatial environment to solve path-finding problems, which costs too much time and energy. Although Hopfield’s mental exploration model makes up for the deficiency mentioned above, the path is still not efficient enough. Moreover, his model mainly focused on the artificial neural network, and clear physiological meanings has not been addressed. In this work, based on the concept of mental exploration, neural energy coding theory has been applied to the novel calculation model to solve the path-finding problem. Energy field is constructed on the basis of the firing power of place cell clusters, and the energy field gradient can be used in mental exploration to solve path-finding problems. The study shows that the new mental exploration model can efficiently find the optimal path, and present the learning process with biophysical meaning as well. We also analyzed the parameters of the model which affect the path efficiency. This new idea verifies the importance of place cell and synapse in spatial memory and proves that energy coding is effective to study cognitive activities. This may provide the theoretical basis for the neural dynamics mechanism of spatial memory.     

Suppression of alternans and conduction blocks despite steep APD restitution: electrotonic, memory, and conduction velocity restitution effects

We examine the utility of the action potential (AP) duration (APD) restitution curve slope in predicting the onset of electrical alternans when electrotonic and memory effects are considered. We develop and use two ionic cell models without memory that have the same restitution curve with slope >1 but different AP shapes and, therefore, different electrotonic effects. We also study a third cell model that incorporates short-term memory of previous cycle lengths, so that it has a family of S1-S2 restitution curves as well as a dynamic restitution curve with slope >1. Our results indicate that both electrotonic and memory effects can suppress alternans, even when the APD restitution curve is steep. In the absence of memory, electrotonic currents related to the shape of the AP, as well as conduction velocity restitution, can affect how alternans develops in tissue and, in some cases, can prevent its induction entirely, even when isolated cells exhibit alternans. When short-term memory is included, alternans may not occur in isolated cells, despite a steep APD restitution curve, and may or may not occur in tissue, depending on conduction velocity restitution. We show for the first time that electrotonic and memory effects can prevent conduction blocks and stabilize reentrant waves in two and three dimensions. Thus we find that the slope of the APD restitution curve alone does not always well predict the onset of alternans and that incorporating electrotonic and memory effects may provide a more useful alternans criterion.     

Information storage matrices in neural networks

A new neural network model with feedback based on the concept of information storage matrices is proposed. This model is similar to the Hopfield and spectral type neural networks but has a more general structure. The presentation gives a fully developed theory for first-order networks, including results on the formation of fixed points and their domains of attraction. These results are used to determine, in deterministic sense, the information storage capacity. The algorithm is applied to the DNA sequencing problem. It is demonstrated how a hidden genetic information in an arbitrary long DNA strand can be extracted.