- Research Article
31
- 10.1016/j.neunet.2012.02.018
A forecast-based STDP rule suitable for neuromorphic implementation
- Feb 14, 2012
- Neural Networks
- S Davies + 3 more +3
A forecast-based STDP rule suitable for neuromorphic implementation
In sensory neural system, external asynchronous stimuli play an important role in perceptual learning, associative memory and map development. However, the organization of structure and dynamics of neural networks induced by external asynchronous stimuli are not well understood. Spike-timing-dependent plasticity (STDP) is a typical synaptic plasticity that has been extensively found in the sensory systems and that has received much theoretical attention. This synaptic plasticity is highly sensitive to correlations between pre-and postsynaptic firings. Thus, STDP is expected to play an important role in response to external asynchronous stimuli, which can induce segregative pre-and postsynaptic firings. In this paper, we study the impact of external asynchronous stimuli on the organization of structure and dynamics of neural networks through STDP. We construct a two-dimensional spatial neural network model with local connectivity and sparseness, and use external currents to stimulate alternately on different spatial layers. The adopted external currents imposed alternately on spatial layers can be here regarded as external asynchronous stimuli. Through extensive numerical simulations, we focus on the effects of stimulus number and inter-stimulus timing on synaptic connecting weights and the property of propagation dynamics in the resulting network structure. Interestingly, the resulting feedforward structure induced by stimulus-dependent asynchronous firings and its propagation dynamics reflect both the underlying property of STDP. The results imply a possible important role of STDP in generating feedforward structure and collective propagation activity required for experience-dependent map plasticity in developing in vivo sensory pathways and cortices. The relevance of the results to cue-triggered recall of learned temporal sequences, an important cognitive function, is briefly discussed as well. Furthermore, this finding suggests a potential application for examining STDP by measuring neural population activity in a cultured neural network.
Loading PDF
A forecast-based STDP rule suitable for neuromorphic implementation
A forecast-based STDP rule suitable for neuromorphic implementation
A compact reconfigurable mixed-signal implementation of synaptic plasticity in spiking neurons
We present a compact mixed-signal implementation of synaptic plasticity for both Spike Timing Dependent Plasticity (STDP) and Spike Timing Dependent Delay Plasticity (STDDP). The proposed mixed-signal implementation consists of an a VLSI time window generator and a digital adaptor. The weight and delay values are stored in a digital memory, and the adaptor will send these values to the time window generator using a digital spike of which the duration is modulated according to these values. The analogue time window generator will then generate a time window, which is required for the implementation of STDP and STDDP. The digital adaptor will carry out the weight/delay adaption using this time window. The aVLSI time window generator is compact (50 μm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> in IBM 130nm process) and we use a time multiplexing approach to achieve up to 65536 (64k) virtual digital adaptors with one physical adaptor, consuming only a fraction of the hardware resource on a Virtex 6 FPGA. Since the digital adaptor has been implemented on an FPGA, it can be easily reconfigured for different adaptation algorithms, which leaves it open for future development. Our mixed-signal implementation is therefore practical for implementing the synaptic plasticity in large-scale spiking neural networks running in real time. We show circuit simulation results illustrating both weight and delay adaptation.
Read moreSTDP induced synchrony in inhibitory neural networks: theory and experiments
Gamma rhythms have been the focus of significant research interest within the neuroscience community in recent years [1]. Earlier theoretical studies focused on the question: how can a network of GABA containing neurons generate gamma oscillations? The findings suggest that for non-instantaneous synaptic events, inhibition rather than excitation is a better synchronizing mechanism for the generation of gamma rhythms [2]. Synchrony in inhibitory neural networks however is extremely sensitive to intrinsic heterogeneity in the network [3]. Based on the evidence for spike timing dependent plasticity (STDP) in inhibitory neurons [4,5], we hypothesize that STDP of inhibitory synapses can promote robust neural synchrony in inhibitory neuronal networks in the presence of heterogeneity. We investigate our hypothesis in a computational (Figure (Figure1a)1a) and a hybrid (Figure (Figure1b)1b) uni-directionally coupled network (UCI) of two fast-spiking inhibitory neurons. In the computational model, each neuron is modeled using the Hodgkin-Huxley (HH) framework [4]. Heterogeneity (H) is modeled by the difference in the intrinsic firing activity of the coupled neurons resulting from different DC current input. In the presence of STDP, the strength of synaptic coupling between the coupled neurons is modeled using a linear additive rule as: gs(t) = gs(t – 1) + ΔgSTDP(Δt), where Δt = tA – tB is the time interval between successive spikes of the post-synaptic and the pre-synaptic neurons and ΔgSTDP is the STDP rule adapted from [4]. In Figure Figure1a,1a, we demonstrate the effect of STDP on synchrony between coupled neurons in the presence of and the absence of STDP for network heterogeneity H=12%. Theoretical analysis using the concept of spike time response curves and Arnold tongue revealed that STDP induced 1:1 synchrony in the UCI network is (i) robust against a large range of heterogeneity in the intrinsic firing activity of coupled neurons, and (ii) in-phase i.e., Δt ≈ 0. Furthermore, the time to in-phase synchronization increases with increasing heterogeneity. Figure 1 a) Theoretical model of UCI. Autaptic synapse is introduced to mimic spike frequency adaptation in neuronal firing activity. b) Hybrid UCI network. Dynamic clamp experimental results for experimental protocol with fixed static-synaptic strength gs(0)=0.5 ... We used the dynamic clamp technique to construct a hybrid UCI network consisting of an HH based model of a inhibitory neuron coupled to a living inhibitory neuron in the stratum oriens of area CA1 of the hippocampus. Whole cell patch clamp recordings were obtained from the live cell under the following experimental protocols: (i) Fix H, vary the static synapse coupling strength gs(0) and (ii) Fix static synapse coupling strength gs(0) and vary H. In Figure Figure1b,1b, we present results from the second experimental protocol. We see that as predicted by our theoretical model, the time to in phase neural synchrony in the hybrid UCI network increases with increasing heterogeneity. We conclude that STDP of inhibitory synapses is a putative mechanism for robust neural synchrony in inhibitory neuronal networks.
Read more<title>Dynamic neural network for visual memory</title>
A dynamic neural network with neural computing units that exhibit hysteresis phenomena is proposed as a mechanism for visual memory. The neural network, named the PN-processor, is loosely based on a mathematical theory proposed by Wilson and Cowan to describe the functional dynamics of conical nervous tissue. The individual neural computing units of the network are programmed to exhibit localized hysteresis phenomena. This neural network structure is capable of storing visual information without physical changes to its synaptic connections. External stimuli move the network's neural activity around a high-dimensional phase space of state attractors until the overall response is stabilized. Once stabilized, the response remains unperturbed by weak or familiar stimuli and is changed only by a sufficiently strong new input. In this paper we briefly describe several aspects of this type of visual memory.
Read moreA Heterosynaptic Spiking Neural System for the Development of Autonomous Agents
Artificial neural systems for computation were first proposed three quarters of a century ago and the concepts developed by the pioneers still shape the field today. The first generation of neural systems was developed in the nineteen forties in the context of analogue electronics and the theoretical research in logic and mathematics that led to the first digital computers in nineteen forties and fifties. The second generation of neural systems implemented on digital computers was born in the nineteen fifties and great progress was made in the subsequent half century with neural networks being applied to many problems in pattern recognition and machine learning. Through this history there has been an interplay between biologically inspired neural systems and their implementation by engineers on digital machines. This thesis concerns the third generation of neural networks, Spiking Neural Networks, which is making possible the creation of new kinds of brain inspired computing architectures that offer the potential to increase the level of realism and sophistication in terms of autonomous machine behaviour and cognitive computing. This thesis presents the development and demonstration of a new theoretical architecture for third generation neural systems, the Integrate-and-Fire based Spiking Neural Model with extended Neuro-modulated Spike Timing Dependent Plasticity capabilities. This proposed architecture overcomes the limitation of the homosynaptic architecture underlying existing implementations of spiking neural networks that it lacks a natural spike timing dependent plasticity regulation mechanism, and this results in ‘run away’ dynamics. To overcome this ad hoc procedures have been implemented to overcome the ‘run away’ dynamics that emerge from the use of spike timing dependent plasticity among other hebbian-based plasticity rules. The new heterosynaptic architecture presented, explicitly abstracts the modulation of complex biochemical mechanisms into a simplified mechanism that is suitable for the engineering of artificial systems with low computational complexity. Neurons work by receiving input signals from other neurons through synapses. The difference between homosynaptic and heterosynaptic plasticity is that, in the former the change in the properties of a synapse (e.g. synaptic efficacy) depends on the point to point activity in either of the sending and receiving neurons, in contrast for heterosynaptic plasticity the change in the properties of a synapse can be elicited by neurons that are not necessary presynaptic or postsynaptic to the synapse in question. The new architecture is tested by a number of implementations in simulated and real environments. This includes experiments with a simulation environment implemented in Netlogo, and an implementation using Lego Mindstorms as the physical robot platform. These experiments demonstrate the problems with the traditional Spike timing dependent plasticity homosynaptic architecture and how the new heterosynaptic approach can overcome them. It is concluded that the new theoretical architecture provides a natural, theoretically sound, and practical new direction for research into the role of modulatory neural systems applied to spiking neural networks.
Read moreA Compositional Framework for Neural Network Modeling Using Typed Petri Nets
The increasing complexity of modern neural networks impedes systematic understanding and formal analysis,often resulting in “black box” behavior. Our paper introduces Typed Petri Nets (TPNs) as a formal framework formodeling the structure and dynamics of neural networks, aiming to address these challenges. We define the corecomponents of TPNs―places, transitions, arcs, a type system (e.g., for tensors), and computation assignments―anddemonstrate how they can compositionally represent basic network layers. Furthermore, we illustrate the capability ofTPNs to model advanced architectures, including convolutional layers, skip connections, and multi-branch structures.TPN dynamics naturally simulate forward propagation through markings and firing rules. The framework’sformal semantics can be rigorously explored using category theory, as illustrated by applications in probabilistic contextsusing Markov Categories. Key advantages of the TPN approach include modularity through compositionality,explicit information flow representation, type safety, and a foundation for formal analysis. This work establishesTPN as a structured, mathematically grounded perspective for understanding complex neural networks, offering apromising basis for future research into learning dynamics, verification, and tool development.
Read moreNonlinear systems identification and control via dynamic multitime scales neural networks.
This paper deals with the adaptive nonlinear identification and trajectory tracking via dynamic multilayer neural network (NN) with different timescales. Two NN identifiers are proposed for nonlinear systems identification via dynamic NNs with different timescales including both fast and slow phenomenon. The first NN identifier uses the output signals from the actual system for the system identification. In the second NN identifier, all the output signals from nonlinear system are replaced with the state variables of the NNs. The online identification algorithms for both NN identifier parameters are proposed using Lyapunov function and singularly perturbed techniques. With the identified NN models, two indirect adaptive NN controllers for the nonlinear systems containing slow and fast dynamic processes are developed. For both developed adaptive NN controllers, the trajectory errors are analyzed and the stability of the systems is proved. Simulation results show that the controller based on the second identifier has better performance than that of the first identifier.
Read moreReinforcement learning method for continuous state space based on dynamic neural network
One of the difficulties encountered in the application of reinforcement learning methods to real-world problem is the generalization of large-scale or continuous state space. In order to solve the curse of dimensionality problem caused by discretizing continuous state space, a kind of Q-learning method for continuous state space based on a dynamic Elman neural network was proposed in this paper. The inputs and the output of Elman network are the system state-action pair and the corresponding Q-value. That is, Elman network is used to estimate the Q-value of state-action pair on-line. Eligibility trace for connecting weights is introduced by borrowing ideas from the eligibility trace mechanism of state in temporal difference algorithm to improve the learning speed of neural network. Computer simulations on mountain car control illustrate the performance and applicability of the proposed Q-learning scheme.
Read moreMathematical studies of the dynamics of finite-size binary neural networks: A review of recent progress.
Several mathematical approaches to studying analytically the dynamics of neural networks rely on mean-field approximations, which are rigorously applicable only to networks of infinite size. However, all existing real biological networks have finite size, and many of them, such as microscopic circuits in invertebrates, are composed only of a few tens of neurons. Thus, it is important to be able to extend to small-size networks our ability to study analytically neural dynamics. Analytical solutions of the dynamics of small-size neural networks have remained elusive for many decades, because the powerful methods of statistical analysis, such as the central limit theorem and the law of large numbers, do not apply to small networks. In this article, we critically review recent progress on the study of the dynamics of small networks composed of binary neurons. In particular, we review the mathematical techniques we developed for studying the bifurcations of the network dynamics, the dualism between neural activity and membrane potentials, cross-neuron correlations, and pattern storage in stochastic networks. Then, we compare our results with existing mathematical techniques for studying networks composed of a finite number of neurons. Finally, we highlight key challenges that remain open, future directions for further progress, and possible implications of our results for neuroscience.
Read moreFinite Impulse Response Neural Networks with Applications in Speed Control of DC Motor Drive
An increasing number of applications of dynamic neural networks has been developed for digital signal processing (DSP), dynamic neural networks are feedforward neural networks with commonly used scalar synapses replaced by linear filters. This provides feedforward neural networks with the capability of performing dynamic mappings, which depend on past input values, dynamic neural networks are suitable for time series prediction, nonlinear system identification, and signal processing applications. Their most popular types are Finite Impulse Response (FIR) neural networks, which are obtained by replacing synapses with finite impulse response filters. Due to their guaranteed stability characteristic and easy to minimize error surface they have been used with great success in many applications such as signal enhancement, noise cancellation, classification of input patterns, system identification, prediction, and control.. Most of the works on system identification using neural networks are based on multilayer feedforward neural networks with backpropagation learning or more efficient variations of this algorithm, an elegant method for training layered networks. This paper is based on work in a Dynamic System Modeling (DYSMO) and as an application for speed control of DC motor drive.
Read moreRanking of Search Requests in the Digital Information Retrieval System Based on Dynamic Neural Networks
The article is devoted to the problem of optimization of search request ranking algorithms in the digital information retrieval system. The algorithm of functioning of the neural network ranking unit based on Hopfield neural network is built. The ability to generate a ranked list of pages found as a result of the request in the digital information retrieval system can be provided by solving two problems of integer optimization: the problem of assignment of combinatorial sets of criteria for assessing the relevance of web page search and the problem of sorting of numbers—relevance values. The architecture of the neural network model based on the dynamic Hopfield neural network with binary output function designed for combinatorial optimization of the final list of documents found in the digital information retrieval system was synthesized. Promising variants of neural network models with binary output function of neurons for synthesis of the optimal evaluation plan with a combinatorial set of criteria by solving the problem of assignment were built. It has been proven that the built models differ in the rules for determining the coefficients of synaptic connections and external shifts; each of the created rules can be used independently or in different combinations with one another. In the course of analytical research, it was found that the optimization formulation of the problem of sorting of relevance values of search pages is identical to the problem of assignment of combinatorial groups of evaluation criteria provided that the elements of the performance matrix of the latter are defined as linear combinations of relevance values.
Read moreChains of discrete-time chaotic neural networks for generation of broadband signals with applications in improved ciphering systems
This paper presents a new approach for generating broadband noise-like signals by exploiting chaotic dynamics in small recurrent neural networks. A new neural network structure, the chain of chaotic neural networks (CCNN) is introduced in order to obtain a high degree of scrambling for the output signal. Comparing with other chaotic or pseudo-random sequence generators, this one has improved characteristics which make them very attractive for using in various applications where a deterministic but having white-noise like properties signals are needed. Fixed point implementation effects were investigated, simulation results proving that such systems may be efficiently implemented in digital technology and thus offering very well protected ciphering sequences.
Read moreDynamics of realistic neural network with time-dependent external signal
Dynamics of realistic neural network with time-dependent external signal
Competitive behaviors of a spiking neural network with spike timing dependent plasticity
Spike timing dependent plasticity (STDP) learning rule is one of hot topics in neurobiology since it's been widely believed that synaptic plasticity mainly contribute to learning and memory in brain. Up to now, STDP has been observed in a wide variety of areas of brain, hippocampus, cortex and so on. Competition among synapses is an important behavior for this learning rule. In present study, we propose a single layer spiking neural network model using STDP learning rule in inhibitory synapses to investigate the competitive behavior. The experiments show that the synapses among neurons are both strengthened on the whole training process. Thus neurons inhibit the activities of one another, eventually the neuron with the highest input spike rate win the competition. We have found that the behavior is efficient when the differences of firing rates of input neurons without STDP are great than 5Hz, otherwise the winner neuron is random. In order to use the principle to artificial intelligent system, we use a mechanism of dynamic learning rate to let the neuron with the highest input to be selected by the competitive behavior as the winner. Therefore, a robust competitive spiking neural network is obtained.
Read moreDynamic attention-integrated neural network for session-based news recommendation
Online news recommendation aims to continuously select a pool of candidate articles that meet the temporal dynamics of user preferences. Most of the existing methods assume that all user-item interaction history are equally importance for recommendation, which is not alway applied in real-word scenario since the user-item interactions are sometime full of stochasticity and contingency. In addition, previous work on session-based algorithms only considers user sequence behaviors within current session without incorporating users’ historical interests or pointing out users’ main purposes within such session. In this paper, we propose a novel neural network framework, dynamic attention-integrated neural network, to tackle the problems. Specifically, we propose a dynamic neural network to model users’ dynamic interests over time in a unified framework for personalized news recommendations. News article semantic embedding, user interests modelling, session-based public behavior mining and an attention scheme that used to learn the attention score of user and item interaction within sessions are four key factors for online sequences mining and recommendation strategy. Experimental results on three real-world datasets show significant improvements over several baselines and state-of-the-art methods on session-based neural networks.
Read more