DL-ReSuMe: A Delay Learning-Based Remote Supervised Method for Spiking Neurons

Taherkhani, Aboozar; Belatreche, Ammar; Li, Yuhua; Maguire, Liam

doi:10.1109/tnnls.2015.2404938

Cited by 87 publications

(57 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each input neuron is randomly connected to a fraction number of hidden neurons as used in [18]. The LIF neuron model described in [41] is used. The proposed method trains the spiking network by adjusting the learning parameters of the hidden and output neurons in parallel.…”

Section: Methodsmentioning

confidence: 99%

“…Consider a pattern from class i is applied to the network and an actual output of the network is generated. The correlation between the actual output and the corresponding desired spike train of the class i is called c i which is calculated by the method used in [41] as in…”

Section: Classification Ability Of the Proposed Methodsmentioning

confidence: 99%

“…Delays of spike propagation are an important characteristic of real biological neural systems, and they have a significant effect on the information processing ability of the nervous system [18], [41], [42]. In extended delay learning (EDL) based ReSuMe [43], for SNs, and in DL-ReSuMe [41], a delay learning-based remote supervised method for SNs, investigated the viability of adjusting the neuron synaptic weights and delays for training a single SN to map a given spatiotemporal input pattern into a desired output spike train. STDP and anti-STDP were used to adjust the synaptic weights, and a delay shift approach was used to adjust their delays.…”

Section: Background and Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A Supervised Learning Algorithm for Learning Precise Timing of Multiple Spikes in Multilayer Spiking Neural Networks

Taherkhani

Belatreche

et al. 2018

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

There is a biological evidence to prove information is coded through precise timing of spikes in the brain. However, training a population of spiking neurons in a multilayer network to fire at multiple precise times remains a challenging task. Delay learning and the effect of a delay on weight learning in a spiking neural network (SNN) have not been investigated thoroughly. This paper proposes a novel biologically plausible supervised learning algorithm for learning precisely timed multiple spikes in a multilayer SNNs. Based on the spike-timing-dependent plasticity learning rule, the proposed learning method trains an SNN through the synergy between weight and delay learning. The weights of the hidden and output neurons are adjusted in parallel. The proposed learning method captures the contribution of synaptic delays to the learning of synaptic weights. Interaction between different layers of the network is realized through biofeedback signals sent by the output neurons. The trained SNN is used for the classification of spatiotemporal input patterns. The proposed learning method also trains the spiking network not to fire spikes at undesired times which contribute to misclassification. Experimental evaluation on benchmark data sets from the UCI machine learning repository shows that the proposed method has comparable results with classical rate-based methods such as deep belief network and the autoencoder models. Moreover, the proposed method can achieve higher classification accuracies than single layer and a similar multilayer SNN.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Classification Ability Of the Proposed Methodsmentioning

confidence: 99%

Section: Background and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Supervised Learning Algorithm for Learning Precise Timing of Multiple Spikes in Multilayer Spiking Neural Networks

Taherkhani

Belatreche

et al. 2018

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…We note that a set of basis functions, along with the weight matrices, describes the spatio-temporal receptive field of the neurons [20]. Examples of basis functions include raised cosines with different synaptic delays [20]- [22], as illustrated in Fig. 2.…”

Section: Dynamic Exponential Family Modelmentioning

confidence: 99%

Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing

Jang

Simeone

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Neuromorphic hardware platforms, such as Intel's Loihi chip, support the implementation of Spiking Neural Networks (SNNs) as an energy-efficient alternative to Artificial Neural Networks (ANNs). SNNs are networks of neurons with internal analogue dynamics that communicate by means of binary time series. In this work, a probabilistic model is introduced for a generalized set-up in which the synaptic time series can take values in an arbitrary alphabet and are characterized by both causal and instantaneous statistical dependencies. The model, which can be considered as an extension of exponential family harmoniums to time series, is introduced by means of a hybrid directed-undirected graphical representation. Furthermore, distributed learning rules are derived for Maximum Likelihood and Bayesian criteria under the assumption of fully observed time series in the training set.

show abstract

“…The most documented evidence for supervised learning in the central nervous system (CNS) comes from the studies on the cerebellum and the cerebellar cortex [21], [22]. However, the exact mechanisms underlying supervised learning in the biological neurons remain an open problem [23], [24]. To date, many supervised learning methods have been proposed in order to train the spiking neurons to generate desired sequences of spikes.…”

Section: Introductionmentioning

confidence: 99%

A Highly Effective and Robust Membrane Potential-Driven Supervised Learning Method for Spiking Neurons

Zhang

Belatreche

et al. 2019

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

Spiking neurons are becoming increasingly popular owing to their biological plausibility and promising computational properties. Unlike traditional rate-based neural models, spiking neurons encode information in the temporal patterns of the transmitted spike trains, which makes them more suitable for processing spatiotemporal information. One of the fundamental computations of spiking neurons is to transform streams of input spike trains into precisely timed firing activity. However, the existing learning methods, used to realize such computation, often result in relatively low accuracy performance and poor robustness to noise. In order to address these limitations, we propose a novel highly effective and robust membrane potential-driven supervised learning (MemPo-Learn) method, which enables the trained neurons to generate desired spike trains with higher precision, higher efficiency, and better noise robustness than the current state-of-the-art spiking neuron learning methods. While the traditional spike-driven learning methods use an error function based on the difference between the actual and desired output spike trains, the proposed MemPo-Learn method employs an error function based on the difference between the output neuron membrane potential and its firing threshold. The efficiency of the proposed learning method is further improved through the introduction of an adaptive strategy, called skip scan training strategy, that selectively identifies the time steps when to apply weight adjustment. The proposed strategy enables the MemPo-Learn method to effectively and efficiently learn the desired output spike train even when much smaller time steps are used. In addition, the learning rule of MemPo-Learn is improved further to help mitigate the impact of the input noise on the timing accuracy and reliability of the neuron firing dynamics. The proposed learning method is thoroughly evaluated on synthetic data and is further demonstrated on real-world classification tasks. Experimental results show that the proposed method can achieve high learning accuracy with a significant improvement in learning time and better robustness to different types of noise.

show abstract

DL-ReSuMe: A Delay Learning-Based Remote Supervised Method for Spiking Neurons

Cited by 87 publications

References 40 publications

A Supervised Learning Algorithm for Learning Precise Timing of Multiple Spikes in Multilayer Spiking Neural Networks

A Supervised Learning Algorithm for Learning Precise Timing of Multiple Spikes in Multilayer Spiking Neural Networks

Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing

A Highly Effective and Robust Membrane Potential-Driven Supervised Learning Method for Spiking Neurons

Contact Info

Product

Resources

About