Artificial Spiking Neural Networks Research Articles

Interfacing in silico and in vitro neuronal networks.

In this study, an in vitro cortical culture was stimulated according to the activity exhibited by its in silico counterpart. We connected the latter, an artificial spiking neural network (SNN), to the former, a biological network (BNN), via an open-loop (i.e. unidirectional) configuration, with the ultimate goal of establishing a closed-loop bidirectional connection in future studies. We detected network bursts in the SNN and utilized them as triggers for stimulus delivery to the BNN. We analyzed evoked BNN responses to evaluate whether the BNN activity was entrained by the SNN by correlating stimuli and BNN evoked network burst rates at different timescales. We found that this correlation was nearly constant at all timescales, but its magnitude depended on the efficacy of the stimulation source in entraining BNN activity.

Healthy and pathological cerebellar Spiking Neural Networks in Vestibulo-Ocular Reflex.

Since the Marr-Albus model, computational neuroscientists have been developing a variety of models of the cerebellum, with different approaches and features. In this work, we developed and tested realistic artificial Spiking Neural Networks inspired to this brain region. We tested in computational simulations of the Vestibulo-Ocular Reflex protocol three different models: a network equipped with a single plasticity site, at the cortical level; a network equipped with a distributed plasticity, at both cortical and nuclear levels; a network with a pathological plasticity mechanism at the cortical level. We analyzed the learning performance of the three different models, highlighting the behavioral differences among them. We proved that the model with a distributed plasticity produces a faster and more accurate cerebellar response, especially during a second session of acquisition, compared with the single plasticity model. Furthermore, the pathological model shows an impaired learning capability in Vestibulo-Ocular Reflex acquisition, as found in neurophysiological studies. The effect of the different plasticity conditions, which change fast and slow dynamics, memory consolidation and, in general, learning capabilities of the cerebellar network, explains differences in the behavioral outcome.

Operant conditioning: a minimal components requirement in artificial spiking neurons designed for bio-inspired robot's controller.

In this paper, we investigate the operant conditioning (OC) learning process within a bio-inspired paradigm, using artificial spiking neural networks (ASNN) to act as robot brain controllers. In biological agents, OC results in behavioral changes learned from the consequences of previous actions, based on progressive prediction adjustment from rewarding or punishing signals. In a neurorobotics context, virtual and physical autonomous robots may benefit from a similar learning skill when facing unknown and unsupervised environments. In this work, we demonstrate that a simple invariant micro-circuit can sustain OC in multiple learning scenarios. The motivation for this new OC implementation model stems from the relatively complex alternatives that have been described in the computational literature and recent advances in neurobiology. Our elementary kernel includes only a few crucial neurons, synaptic links and originally from the integration of habituation and spike-timing dependent plasticity as learning rules. Using several tasks of incremental complexity, our results show that a minimal neural component set is sufficient to realize many OC procedures. Hence, with the proposed OC module, designing learning tasks with an ASNN and a bio-inspired robot context leads to simpler neural architectures for achieving complex behaviors.

Spike-Based Synaptic Plasticity in Silicon: Design, Implementation, Application, and Challenges

The ability to carry out signal processing, classification, recognition, and computation in artificial spiking neural networks (SNNs) is mediated by their synapses. In particular, through activity-dependent alteration of their efficacies, synapses play a fundamental role in learning. The mathematical prescriptions under which synapses modify their weights are termed synaptic plasticity rules. These learning rules can be based on abstract computational neuroscience models or on detailed biophysical ones. As these rules are being proposed and developed by experimental and computational neuroscientists, engineers strive to design and implement them in silicon and en masse in order to employ them in complex real-world applications. In this paper, we describe analog very large-scale integration (VLSI) circuit implementations of multiple synaptic plasticity rules, ranging from phenomenological ones (e.g., based on spike timing, mean firing rates, or both) to biophysically realistic ones (e.g., calcium-dependent models). We discuss the application domains, weaknesses, and strengths of various representative approaches proposed in the literature, and provide insight into the challenges that engineers face when designing and implementing synaptic plasticity rules in VLSI technology for utilizing them in real-world applications.

Habituation: a non-associative learning rule design for spiking neurons and an autonomous mobile robots implementation

This paper presents a novel bio-inspired habituation function for robots under control by an artificial spiking neural network. This non-associative learning rule is modelled at the synaptic level and validated through robotic behaviours in reaction to different stimuli patterns in a dynamical virtual 3D world. Habituation is minimally represented to show an attenuated response after exposure to and perception of persistent external stimuli. Based on current neurosciences research, the originality of this rule includes modulated response to variable frequencies of the captured stimuli. Filtering out repetitive data from the natural habituation mechanism has been demonstrated to be a key factor in the attention phenomenon, and inserting such a rule operating at multiple temporal dimensions of stimuli increases a robot's adaptive behaviours by ignoring broader contextual irrelevant information.

Classical conditioning in different temporal constraints: an STDP learning rule for robots controlled by spiking neural networks

This work investigates adaptive behaviours for an intelligent robotic agent when subjected to temporal stimuli consisting of associations of contextual cues and simple reflexes. This is made possible thanks to a novel learning rule based on spike-timing-dependent plasticity and embedded in an artificial spiking neural network serving as a brain-like controller. The subsequent bio-inspired cognitive system carries out different classical conditioning tasks in a controlled virtual 3D-world while the timing and frequency of unconditioned and conditioned parameters are varied. The results of this simulated robotic environment are analysed at different stages from stimuli capture to neural spike generation and show extended behavioural capabilities by the robot in the temporal domain.

A spiking neural network based cortex-like mechanism and application to facial expression recognition.

In this paper, we present a quantitative, highly structured cortex-simulated model, which can be simply described as feedforward, hierarchical simulation of ventral stream of visual cortex using biologically plausible, computationally convenient spiking neural network system. The motivation comes directly from recent pioneering works on detailed functional decomposition analysis of the feedforward pathway of the ventral stream of visual cortex and developments on artificial spiking neural networks (SNNs). By combining the logical structure of the cortical hierarchy and computing power of the spiking neuron model, a practical framework has been presented. As a proof of principle, we demonstrate our system on several facial expression recognition tasks. The proposed cortical-like feedforward hierarchy framework has the merit of capability of dealing with complicated pattern recognition problems, suggesting that, by combining the cognitive models with modern neurocomputational approaches, the neurosystematic approach to the study of cortex-like mechanism has the potential to extend our knowledge of brain mechanisms underlying the cognitive analysis and to advance theoretical models of how we recognize face or, more specifically, perceive other people's facial expression in a rich, dynamic, and complex environment, providing a new starting point for improved models of visual cortex-like mechanism.

Spiking Neurons With ASNN Based-Methods for the Neural Block Cipher

Problem statement: This paper examines Artificial Spiking Neural Network (ASNN) which inter-connects group of artificial neurons that uses a mathematical model with the aid of block cipher. The aim of undertaken this research is to come up with a block cipher where by the keys are randomly generated by ASNN which can then have any variable block length. This will show the private key is kept and do not have to be exchange to the other side of the communication channel so it present a more secure procedure of key scheduling. The process enables for a faster change in encryption keys and a network level encryption to be implemented at a high speed without the headache of factorization. Approach: The block cipher is converted in public cryptosystem and had a low level of vulnerability to attack from brute, and moreover can able to defend against linear attacks since the Artificial Neural Networks (ANN) architecture convey non-linearity to the encryption/decryption procedures. Result: In this paper is present to use the Spiking Neural Networks (SNNs) with spiking neurons as its basic unit. The timing for the SNNs is considered and the output is encoded in 1’s and 0’s depending on the occurrence or not occurrence of spikes as well as the spiking neural networks use a sign function as activation function, and present the weights and the filter coefficients to be adjust, having more degrees of freedom than the classical neural networks. Conclusion: In conclusion therefore, encryption algorithm can be deployed in communication and security applications where data transfers are most crucial. So this paper, the neural block cipher proposed where the keys are generated by the SNN and the seed is considered the public key which generates the both keys on both sides In future therefore a new research will be conducted on the Spiking Neural Network (SNN) impacts on communication.

Real-time classification of datasets with hardware embedded neuromorphic neural networks

Neuromorphic artificial neural networks attempt to understand the essential computations that take place in the dense networks of interconnected neurons making up the central nervous systems in living creatures. This article demonstrates that artificial spiking neural networks--built to resemble the biological model--encoding information in the timing of single spikes, are capable of computing and learning clusters from realistic data. It shows how a spiking neural network based on spike-time coding can successfully perform unsupervised and supervised clustering on real-world data. A temporal encoding procedure of continuously valued data is developed, together with a hardware implementation oriented new learning rule set. Solutions that make use of embedded soft-core microcontrollers are investigated, to implement some of the most resource-consuming components of the artificial neural network. Details of the implementations are given, with benchmark application evaluation and test bench description. Measurement results are presented, showing real-time and adaptive data processing capabilities, comparing these to related findings in the specific literature.

Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity

The persistent modification of synaptic efficacy as a function of the relative timing of pre- and postsynaptic spikes is a phenomenon known as spike-timing-dependent plasticity (STDP). Here we show that the modulation of STDP by a global reward signal leads to reinforcement learning. We first derive analytically learning rules involving reward-modulated spike-timing-dependent synaptic and intrinsic plasticity, by applying a reinforcement learning algorithm to the stochastic spike response model of spiking neurons. These rules have several features common to plasticity mechanisms experimentally found in the brain. We then demonstrate in simulations of networks of integrate-and-fire neurons the efficacy of two simple learning rules involving modulated STDP. One rule is a direct extension of the standard STDP model (modulated STDP), and the other one involves an eligibility trace stored at each synapse that keeps a decaying memory of the relationships between the recent pairs of pre- and postsynaptic spike pairs (modulated STDP with eligibility trace). This latter rule permits learning even if the reward signal is delayed. The proposed rules are able to solve the XOR problem with both rate coded and temporally coded input and to learn a target output firing-rate pattern. These learning rules are biologically plausible, may be used for training generic artificial spiking neural networks, regardless of the neural model used, and suggest the experimental investigation in animals of the existence of reward-modulated STDP.

NeuroPipe-Chip: A digital neuro-processor for spiking neural networks

Computing complex spiking artificial neural networks (SANNs) on conventional hardware platforms is far from reaching real-time requirements. Therefore we propose a neuro-processor, called NeuroPipe-Chip, as part of an accelerator board. In this paper, we introduce two new concepts on chip-level to speed up the computation of SANNs. These concepts are implemented in a prototype of the NeuroPipe-Chip. We present the hardware structure of the prototype and evaluate its performance in a system simulation based on a hardware description language (HDL). For the computation of a simple SANN for image segmentation, the NeuroPipe-Chip operating at 100 MHz shows an improvement of more than two orders of magnitude compared to an Alpha 500 MHz workstation and approaches real-time requirements for the computation of SANNs in the order of 10(6) neurons. Hence, such an accelerator would allow for applications of complex SANNs to solve real-world tasks like real-time image processing. The NeuroPipe-Chip has been fabricated in an Alcatel 0.35-mum digital CMOS technology.

Learning Methods of Recurrent Spiking Neural Networks

In an artificial Spiking Neural Network (SNN) the information processing and transmission are carried out by spike trains in a manner similar to the generic biological neurons. Recently it has been reported that they are computationally more powerful than the conventional neural networks. Yet, there are no well defined efficient methods for learning due to their rather intricately discontinuous and nonlinear mechanisms. In this paper, we consider a recurrent SNN constructed with integrate-and-fire type spiking neurons. First we propose a learning method such that the SNN possesses desired transient responses (spike-train outputs) by changing the synaptic weights. Further by including periodic state conditions we propose a learning method such that the SNN possesses desired oscillatory responses (limit cycle spike train) by changing both the synaptic weights and the initial conditions. Simulation examples are also provided to verify the efficiency and the applicability of the proposed algorithm.