Spike-timing Dependent Plasticity Learning Rule Research Articles

Mimicking the spike-timing dependent plasticity in HfO2-based memristors at multiple time scales

In this work, TiN/Ti/HfO2/W memristors have been investigated to mimic the spike-time dependent plasticity (STDP) of biological synapses at multiple time scales. For this purpose, a smart software tool has been implemented to control the instrumentation and to perform a dedicated ultra-fast pulsed characterization. Different time scales, from tens of milliseconds to hundreds of nanoseconds, have been explored to emulate the STDP learning rule in electronic synapses. The impact of such times on the synaptic weight potentiation and depression characteristics has also been discussed.

Fully Printed All-Solid-State Organic Flexible Artificial Synapse for Neuromorphic Computing.

Nonvolatile, flexible artificial synapses that can be used for brain-inspired computing are highly desirable for emerging applications such as human-machine interfaces, soft robotics, medical implants, and biological studies. Printed devices based on organic materials are very promising for these applications due to their sensitivity to ion injection, intrinsic printability, biocompatibility, and great potential for flexible/stretchable electronics. Herein, we report the experimental realization of a nonvolatile artificial synapse using organic polymers in a scalable fabrication process. The three-terminal electrochemical neuromorphic device successfully emulates the key features of biological synapses: long-term potentiation/depression, spike timing-dependent plasticity learning rule, paired-pulse facilitation, and ultralow energy consumption. The artificial synapse network exhibits an excellent endurance against bending tests and enables a direct emulation of logic gates, which shows the feasibility of using them in futuristic hierarchical neural networks. Based on our demonstration of 100 distinct, nonvolatile conductance states, we achieved a high accuracy in pattern recognition and face classification neural network simulations.

Passive memristor synaptic circuits with multiple timing dependent plasticity mechanisms

Adaptation of synaptic strength is central to memory and learning in biological systems, enabling important high-level processes such as the ability of animals to respond to a changing environment. Memristor devices are a promising new, nanoscale technology that emulates the function of synapses and can therefore be used to represent synaptic elements in analog artificial neural networks. The main mechanism to carry out unsupervised adaptation of weights in memristive synapses currently involves artificial spiking neural network designs relying on spike-timing dependent plasticity (STDP). We present and analyze a new memristive circuit that in addition to STDP learning rules also implements competitive adjustment based on relative timing of presynaptic inputs. The cooperative effect of multiple learning rules in the new circuit may ameliorate the problem of erasure of synaptic weights.

Restickable Oxide Neuromorphic Transistors with Spike‐Timing‐Dependent Plasticity and Pavlovian Associative Learning Activities

AbstractIn neural system, both spike‐timing‐dependent plasticity (STDP) and conditioned reflex are vital synaptic learning mechanisms to regulate advanced neural activities, being associated with temporally coupled stimuli. Thus, realization of STDP and conditioned reflex on a single solid‐state device may open up new opportunities for neuromorphic engineering. Here, restickable chitosan‐gated oxide neuromorphic transistors are fabricated on polyimide tape. Based on protonic electrochemical doping/de‐doping processes at indium‐tin‐oxide/chitosan interfaces, four types of STDP learning rules are successfully demonstrated, including Hebbian STDP, anti‐Hebbian STDP, symmetrical STDP, and visual STDP. Trained with Hebbian STDP, Pavlovian associative learning and extinction behaviors are demonstrated successfully on a single‐oxide neuromorphic transistor. No complex device circuits are needed. It is interesting to note here that the devices can be pasted on different holders with different curvature radii without degrading the transistor performances and STDP learning rules. Moreover, the proposed oxide neuromorphic transistors can be dissolved in deionized water easily. The results here indicate potential applications of the proposed restickable oxide neuromorphic transistors in flexible neuromorphic cognitive platforms.

Event-Based, Timescale Invariant Unsupervised Online Deep Learning With STDP.

Learning of hierarchical features with spiking neurons has mostly been investigated in the database framework of standard deep learning systems. However, the properties of neuromorphic systems could be particularly interesting for learning from continuous sensor data in real-world settings. In this work, we introduce a deep spiking convolutional neural network of integrate-and-fire (IF) neurons which performs unsupervised online deep learning with spike-timing dependent plasticity (STDP) from a stream of asynchronous and continuous event-based data. In contrast to previous approaches to unsupervised deep learning with spikes, where layers were trained successively, we introduce a mechanism to train all layers of the network simultaneously. This allows approximate online inference already during the learning process and makes our architecture suitable for online learning and inference. We show that it is possible to train the network without providing implicit information about the database, such as the number of classes and the duration of stimuli presentation. By designing an STDP learning rule which depends only on relative spike timings, we make our network fully event-driven and able to operate without defining an absolute timescale of its dynamics. Our architecture requires only a small number of generic mechanisms and therefore enforces few constraints on a possible neuromorphic hardware implementation. These characteristics make our network one of the few neuromorphic architecture which could directly learn features and perform inference from an event-based vision sensor.

Compensation for Traveling Wave Delay Through Selection of Dendritic Delays Using Spike-Timing-Dependent Plasticity in a Model of the Auditory Brainstem

Asynchrony among synaptic inputs may prevent a neuron from responding to behaviorally relevant sensory stimuli. For example, “octopus cells” are monaural neurons in the auditory brainstem of mammals that receive input from auditory nerve fibers (ANFs) representing a broad band of sound frequencies. Octopus cells are known to respond with finely timed action potentials at the onset of sounds despite the fact that due to the traveling wave delay in the cochlea, synaptic input from the auditory nerve is temporally diffuse. This paper provides a proof of principle that the octopus cells' dendritic delay may provide compensation for this input asynchrony, and that synaptic weights may be adjusted by a spike-timing dependent plasticity (STDP) learning rule. This paper used a leaky integrate and fire model of an octopus cell modified to include a “rate threshold,” a property that is known to create the appropriate onset response in octopus cells. Repeated audio click stimuli were passed to a realistic auditory nerve model which provided the synaptic input to the octopus cell model. A genetic algorithm was used to find the parameters of the STDP learning rule that reproduced the microscopically observed synaptic connectivity. With these selected parameter values it was shown that the STDP learning rule was capable of adjusting the values of a large number of input synaptic weights, creating a configuration that compensated the traveling wave delay of the cochlea.

Demonstration of Unsupervised Learning With Spike-Timing-Dependent Plasticity Using a TFT-Type NOR Flash Memory Array

We investigate the characteristics of a synaptic imitation device using a thin-film transistor (TFT)-type NOR flash memory cell with a half-covered floating gate. The long-term potentiation (LTP) and long-term depression (LTD) required for the operation of the spike-timing-dependent plasticity (STDP) algorithm are implemented using the proposed pulse scheme. Unsupervised learning is successfully demonstrated by applying the STDP learning rule through software MATLAB simulation reflecting the LTP/LTD characteristics of the fabricated TFT-type NOR flash memory array. We present the learning and recognition processes of $28\times28$ MNIST handwritten digit patterns. First, STDP learning in a single-neuron string ( $784\times1$ ) is investigated, after which STDP learning is demonstrated in a multineuron array ( $784\times10$ ) with a lateral inhibition function to demonstrate the ability of multipattern learning and recognition. Meanwhile, we investigate the key factors of STDP unsupervised learning. Finally, an approach is suggested to implement a hardware neural network using the conventional CMOS technology for STDP unsupervised learning as a visual pattern recognition system.

Unsupervised Feature Learning With Winner-Takes-All Based STDP.

We present a novel strategy for unsupervised feature learning in image applications inspired by the Spike-Timing-Dependent-Plasticity (STDP) biological learning rule. We show equivalence between rank order coding Leaky-Integrate-and-Fire neurons and ReLU artificial neurons when applied to non-temporal data. We apply this to images using rank-order coding, which allows us to perform a full network simulation with a single feed-forward pass using GPU hardware. Next we introduce a binary STDP learning rule compatible with training on batches of images. Two mechanisms to stabilize the training are also presented : a Winner-Takes-All (WTA) framework which selects the most relevant patches to learn from along the spatial dimensions, and a simple feature-wise normalization as homeostatic process. This learning process allows us to train multi-layer architectures of convolutional sparse features. We apply our method to extract features from the MNIST, ETH80, CIFAR-10, and STL-10 datasets and show that these features are relevant for classification. We finally compare these results with several other state of the art unsupervised learning methods.

Neuromodulated Synaptic Plasticity on the SpiNNaker Neuromorphic System.

SpiNNaker is a digital neuromorphic architecture, designed specifically for the low power simulation of large-scale spiking neural networks at speeds close to biological real-time. Unlike other neuromorphic systems, SpiNNaker allows users to develop their own neuron and synapse models as well as specify arbitrary connectivity. As a result SpiNNaker has proved to be a powerful tool for studying different neuron models as well as synaptic plasticity—believed to be one of the main mechanisms behind learning and memory in the brain. A number of Spike-Timing-Dependent-Plasticity(STDP) rules have already been implemented on SpiNNaker and have been shown to be capable of solving various learning tasks in real-time. However, while STDP is an important biological theory of learning, it is a form of Hebbian or unsupervised learning and therefore does not explain behaviors that depend on feedback from the environment. Instead, learning rules based on neuromodulated STDP (three-factor learning rules) have been shown to be capable of solving reinforcement learning tasks in a biologically plausible manner. In this paper we demonstrate for the first time how a model of three-factor STDP, with the third-factor representing spikes from dopaminergic neurons, can be implemented on the SpiNNaker neuromorphic system. Using this learning rule we first show how reward and punishment signals can be delivered to a single synapse before going on to demonstrate it in a larger network which solves the credit assignment problem in a Pavlovian conditioning experiment. Because of its extra complexity, we find that our three-factor learning rule requires approximately 2× as much processing time as the existing SpiNNaker STDP learning rules. However, we show that it is still possible to run our Pavlovian conditioning model with up to 1 × 104 neurons in real-time, opening up new research opportunities for modeling behavioral learning on SpiNNaker.

Event-Driven Continuous STDP Learning With Deep Structure for Visual Pattern Recognition.

Human beings can achieve reliable and fast visual pattern recognition with limited time and learning samples. Underlying this capability, ventral stream plays an important role in object representation and form recognition. Modeling the ventral steam may shed light on further understanding the visual brain in humans and building artificial vision systems for pattern recognition. The current methods to model the mechanism of ventral stream are far from exhibiting fast, continuous, and event-driven learning like the human brain. To create a visual system similar to ventral stream in human with fast learning capability, in this paper, we propose a new spiking neural system with an event-driven continuous spike timing dependent plasticity (STDP) learning method using specific spiking timing sequences. Two novel continuous input mechanisms have been used to obtain the continuous input spiking pattern sequence. With the event-driven STDP learning rule, the proposed learning procedure will be activated if the neuron receive one pre- or post-synaptic spike event. The experimental results on MNIST database show that the proposed method outperforms all other methods in fast learning scenarios and most of the current models in exhaustive learning experiments.

(Invited) Analog Hfox-Rram Switches for Neural Networks

Memristive systems represent today a disruptive technology for the semiconductor industry with high potential for a wide range of applications ranging from non-volatile memories and non-volatile logic, to analog circuits, biomimetic devices, and neuromorphic computing paradigms. Among the general class of memristive systems, our work focus on oxide filamentary resistive random access memories (oxide RRAM) that base their operation on redox reactions and electrochemical phenomena that allow the formation and dissolution of conductive filaments, shorting the two electrodes of a metal/oxide/metal stack [1]. RRAMs have already demonstrated their great potential for non-volatile memory applications because of low power consumption, fast switching times, scalability down to nm scale [2] or atomic level, and CMOS compatibility. In parallel, significant efforts to redirect the device engineering towards neuromorphic computing [3] and neural networks have been devoted by a large community in the last years. Indeed, the RRAM technology can localize memory and computation in one single device, thus allowing a conceptual realization of non-Von Neumann paradigms that dramatically reduce the power-cost in computing architectures and data communication. This research finds its main application in the development of intelligent and adaptive systems towards the ‘Internet of Things’ concept. It is a highly interdisciplinary research field which merges, on one hand, materials development, nanodevice fabrication, modelling, electrical testing aimed at building artificial synapses with memristive devices. On the other hand, it studies the implementation of neuron functions into VLSI electronics that has to match memristive behavior and electrical features for a functional and physical integration of artificial neuronal and synaptic units. In our work we are focusing on switching dynamics in relation to material properties of HfOx-based RRAM devices [4-7] in order to reach the switching characteristics that fit biologically plausible behaviors. Here we present analog memristive behavior for use in two different approaches, named (i) 1 RRAM-1 synapse and (ii) 1T-1 RRAM–synapse for subthreshold CMOS circuits. In approach (i), a single RRAM device plays the role of a synapse by itself. The analog behavior allows realizing a Spike Timing Dependent-Plasticity (STDP) learning rule (Fig1a), which translates the timing of two superimposing spikes with specific shapes sent to the two device terminals into a causality relation among events [6-9]. The experimental STDP learning rule has been employed in a simulated neuromorphic network able to recognize vowels after an unsupervised training (Fig.1b). While conceptually simple and allowing for a highly compact design, the previous approach is very challenging in practice. The 1T-1 RRAM synapse for subthreshold CMOS circuits, despite being less compact, is more feasible and allows some biological plausibility even within a network utilizing short simply shaped spikes. The use of subthreshold transistor in the analog regime refers back to the original definition of neuromorphic system as given by Carver Mead [9] and is used to generate the biorealistic temporal dynamics of post synaptic spikes [10]. We will demonstrate that RRAM devices can be interfaced with such synaptic circuits including subthreshold transistors to obtain a non-volatile control of synaptic weights. [1] Brivio, G. Tallarida, E. Cianci and S. Spiga, Formation and disruption of conductive filaments in a HfO2/TiN structure, Nanotechnology 25, 385705 (2014) [2] J. Frascaroli , S. Brivio, F. F. Lupi , G. Seguini , L. Boarino , M. Perego, and S. Spiga , Resistive Switching in High-Density Nanodevices Fabricated by Block Copolymer Self-Assembly, ACS Nano 9, 2518 (2015) [3] G. Indiveri, S.-C. Liu, Memory and information processing in neuromorphic systems, In Proceedings of the IEEE, IEEE, volume 103, 2015. [4] J. Frascaroli, F. G. Volpe, S. Brivio, and S. Spiga, Effect of Al doping on the retention behavior of HfO2 resistive switching memories, Microelectronic Engineering 147, 104 (2015) [5] S. Brivio, J. Frascaroli, and S. Spiga, Role of metal-oxide interfaces in the multiple resistance switching regimes of Pt/HfO2/TiN devices, Applied Physics Letters 107, 023504 (2015) [6]E. Covi, S. Brivio, M. Fanciulli, and S. Spiga, Synaptic potentiation and depression in Al:HfO2-based memristor , Microelectronic Engineering 147, 41-44 (2015) [7] S. Brivio, E. Covi, A. Serb, T. Prodromakis, M. Fanciulli, and S. Spiga, Gradual set dynamics in HfO2-based memristor driven by sub-threshold voltage pulses, in Memristive Syst. MEMRISYS 2015 IEEE Int. Conf. On (2015), pp. 1–2. [8] E. Covi, S. Brivio, A. Serb, T. Prodromakis, M. Fanciulli, and S. Spiga, HfO2-based Memristors for Neuromorphic Applications, Proceedings of 2016 IEEE International Symposium on Circuits and Systems (ISCAS) [9] C. Mead, Analog VLSI and neural systems. Reading, MA: Addison-Wesley (1989) [10] Bartolozzi et al., Neural Computation 19 (2007) 2581. Figure 1

Slow feature analysis with spiking neurons and its application to audio stimuli.

Extracting invariant features in an unsupervised manner is crucial to perform complex computation such as object recognition, analyzing music or understanding speech. While various algorithms have been proposed to perform such a task, Slow Feature Analysis (SFA) uses time as a means of detecting those invariants, extracting the slowly time-varying components in the input signals. In this work, we address the question of how such an algorithm can be implemented by neurons, and apply it in the context of audio stimuli. We propose a projected gradient implementation of SFA that can be adapted to a Hebbian like learning rule dealing with biologically plausible neuron models. Furthermore, we show that a Spike-Timing Dependent Plasticity learning rule, shaped as a smoothed second derivative, implements SFA for spiking neurons. The theory is supported by numerical simulations, and to illustrate a simple use of SFA, we have applied it to auditory signals. We show that a single SFA neuron can learn to extract the tempo in sound recordings.

Modeling the interplay between structural plasticity and spike-timing-dependent plasticity

Structural Plasticity describes a form of long-term plasticity, in which the pruning and the creation of synapses lead to the formation of memories in the topology of a network of neurons. In contrast, classical learning rules such as spike-timing dependent plasticity (STDP) focus on changing the efficacy of synapses, for example by looking at the correlation of pre-and post-synaptic activity in spiking neural networks. Typically, prolonged correlated activity leads to a long-term potentiation of the synaptic weight, while anti-correlated activity depresses the weight. We propose a computational model that combines classical learning rules with structural changes in spiking neural network architectures that are based on observations on the morphological changes real biological synapses undergo during their live-cycle. Our model is based on the assumption that newly formed synapses are initially silent, due to their lack of AMPA receptors. In these synapses, only co-activation with other synapses can lead to postsynaptic potentials, and if this co-activation is not present for a critical period, the synapse degenerates again [1]. To study the interaction of structural plasticity and classical STDP learning rules, we simulated a highly recurrently connected spiking neural network and presented topological inputs to its neurons. We implemented the triplet STDP learning rule proposed by Pfister and Gerstner [2], and applied a structural plasticity rule where a critical period is opened whenever a synaptic weight is decreased below a certain threshold. If the weight does not manage to reach a set threshold by the end of the critical period, the synapse is pruned, and a new synapse is instantiated within the network; otherwise the synapse is maintained. This approach implies a homeostasis in the number of consolidated synapses in the network, while keeping the connectivity at a desired level of sparseness. We show in Figure ​Figure11 simulation results in which the input topology of the network is first learned using only STDP, and then, after activating structural plasticity, the structure of the connectivity matrix itself is adapted such that it reflects the input topology. Figure 1 Connectivity matrix from input to target neuron population with and without structural plasticity. Top: Randomly initialized connectivity, learned using triplet STDP. Bottom: Connectivity learned using structural plasticity and triplet-STDP. A major advantage of structural plasticity in artificial neural networks is given by the fact that it allows a drastic increase in performance given a finite number of synaptic resources. In addition to offering a promising approach for optimizing performance in software simulated networks, the model we propose optimizes the usage of resources in dedicated hardware neural network implementations that are faced with limited resources for emulating or simulating synaptic connections. This is particularly relevant for electronic implementations of spiking neural networks, ranging from GPU-based systems to mixed signal analog-digital neuromorphic VLSI devices.

Simple square pulses for implementing spike‐timing‐dependent plasticity in phase‐change memory

Phase‐change memory (PCM) is a promising candidate as an artificial synapse. A compact operation method to implement synaptic functions with low power consumption is critical for constructing large‐scale neuromorphic system. Here we propose a square spike strategy for implementing spike‐timing‐dependent plasticity (STDP) in PCM. Based on the heat accumulation effect in PCM, modulating the time intervals of pre‐ and post‐spikes results in different heat generation and dissipation conditions, which lead to various crystalline/ amorphous ratios in the phase change material layer in devices with diverse synaptic weights. Four forms of STDP learning rule are experimentally demonstrated. This study will further promote the development of PCM technology involved in neuromorphic systems. (© 2015 WILEY‐VCH Verlag GmbH &Co. KGaA, Weinheim)

Competitive STDP Learning of Overlapping Spatial Patterns.

Spike-timing-dependent plasticity (STDP) is a set of Hebbian learning rules firmly based on biological evidence. It has been demonstrated that one of the STDP learning rules is suited for learning spatiotemporal patterns. When multiple neurons are organized in a simple competitive spiking neural network, this network is capable of learning multiple distinct patterns. If patterns overlap significantly (i.e., patterns are mutually inclusive), however, competition would not preclude trained neuron's responding to a new pattern and adjusting synaptic weights accordingly. This letter presents a simple neural network that combines vertical inhibition and Euclidean distance-dependent synaptic strength factor. This approach helps to solve the problem of pattern size-dependent parameter optimality and significantly reduces the probability of a neuron's forgetting an already learned pattern. For demonstration purposes, the network was trained for the first ten letters of the Braille alphabet.

Inheritance of Hippocampal Place Fields Through Hebbian Learning: Effects of Theta Modulation and Phase Precession on Structure Formation.

A place cell is a neuron that fires whenever the animal traverses a particular location of the environment-the place field of the cell. Place cells are found in two regions of the rodent hippocampus: CA3 and CA1. Motivated by the anatomical connectivity between these two regions and by the evidence for synaptic plasticity at these connections, we study how a place field in CA1 can be inherited from an upstream region such as CA3 through a Hebbian learning rule, in particular, through spike-timing-dependent plasticity (STDP). To this end, we model a population of CA3 place cells projecting to a single CA1 cell, and we assume that the CA1 input synapses are plastic according to STDP. With both numerical and analytical methods, we show that in the case of overlapping CA3 input place fields, the STDP learning rule leads to the formation of a place field in CA1. We then investigate the roles of the hippocampal theta modulation and phase precession on the inheritance process. We find that theta modulation favors the inheritance and leads to faster place field formation whereas phase precession changes the drift of CA1 place fields over time.

Network-timing-dependent plasticity.

Bursts of activity in networks of neurons are thought to convey salient information and drive synaptic plasticity. Here we report that network bursts also exert a profound effect on Spike-Timing-Dependent Plasticity (STDP). In acute slices of juvenile rat somatosensory cortex we paired a network burst, which alone induced long-term depression (LTD), with STDP-induced long-term potentiation (LTP) and LTD. We observed that STDP-induced LTP was either unaffected, blocked or flipped into LTD by the network burst, and that STDP-induced LTD was either saturated or flipped into LTP, depending on the relative timing of the network burst with respect to spike coincidences of the STDP event. We hypothesized that network bursts flip STDP-induced LTP to LTD by depleting resources needed for LTP and therefore developed a resource-dependent STDP learning rule. In a model neural network under the influence of the proposed resource-dependent STDP rule, we found that excitatory synaptic coupling was homeostatically regulated to produce power law distributed burst amplitudes reflecting self-organized criticality, a state that ensures optimal information coding.

Exploiting pallidal plasticity for stimulation in Parkinson’s disease

Objective. Continuous application of high-frequency deep brain stimulation (DBS) often effectively reduces motor symptoms of Parkinson’s disease patients. While there is a growing need for more effective and less traumatic stimulation, the exact mechanism of DBS is still unknown. Here, we present a methodology to exploit the plasticity of GABAergic synapses inside the external globus pallidus (GPe) for the optimization of DBS. Approach. Assuming the existence of spike-timing-dependent plasticity (STDP) at GABAergic GPe–GPe synapses, we simulate neural activity in a network model of the subthalamic nucleus and GPe. In particular, we test different DBS protocols in our model and quantify their influence on neural synchrony. Main results. In an exemplary set of biologically plausible model parameters, we show that STDP in the GPe has a direct influence on neural activity and especially the stability of firing patterns. STDP stabilizes both uncorrelated firing in the healthy state and correlated firing in the parkinsonian state. Alternative stimulation protocols such as coordinated reset stimulation can clearly profit from the stabilizing effect of STDP. These results are widely independent of the STDP learning rule. Significance. Once the model settings, e.g., connection architectures, have been described experimentally, our model can be adjusted and directly applied in the development of novel stimulation protocols. More efficient stimulation leads to both minimization of side effects and savings in battery power.

Ferroelectric Artificial Synapses for Recognition of a Multishaded Image

We demonstrate, for the first time, the on-chip pattern recognition of a multishaded grayscale image in a neural network circuit with multiple neurons. This pattern recognition is based on a spiking neural network model that uses multiple three-terminal ferroelectric memristors (3T-FeMEMs) as synapses. The synapse chip of the neural network is formed by stacking CMOS circuits and 3T-FeMEMs. The conductance of the 3T-FeMEM is gradually changed in the linear range by varying the amplitude of the applied voltage pulse. Using the analog and nonvolatile conductance change of the 3T-FeMEM as synaptic weight, the matrix patterns are learned after the spike timing-dependent plasticity learning rule. Even when an incomplete multishaded pattern is input to the neural network circuit, it automatically completes and recalls a previously learned pattern.

基于STDP 规则和忆阻桥突触的神经网络及图像处理

Memristor is a nonlinear circuit element which has property of memory and the similar synapse characteristic. Based on these properties, we presents a memristor bridge synaptic circuit based on the STDP (spike-time-dependent plasticity) learning rule which has an advantage that can be used as a synapse in the arti cial neural network. According to the advantage, we combine the new circuit with other circuits and networks and the bran-new circuits and networks are constructed. Firstly, we combine the memristor bridge synaptic circuit with three additional transistor components and the synaptic calculation of the neural network is realized, and then the complete memristor bridge synaptic neural network is constructed. Secondly, we combine the cellular neural network with it and can be used in image denoising, edge extraction, corner detection and Chinese character recognition. Finally, the feasibility of the proposed method is proved by the a series of the simulation experiments, and the memristor bridge synaptic neural network based on the STDP learning rule has more bionic feasibility, more integrated and more easy to replace the template are demonstrated, and it is hopeful to solve the real-time complex intelligent problems.