EDL: An Extended Delay Learning Based Remote Supervised Method for Spiking Neurons

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

doi:10.1007/978-3-319-26535-3_22

Cited by 10 publications

(17 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The third activity at the time of a desired spike where there are not any actual output spikes of the readout neuron is the adjustment of delays of the readout neuron to increase the PSP of the readout neuron at the desired time, based on EDL [43]. All the abovementioned activities are repeated at the time of other desired spikes in a multispike coding scheme.…”

Section: A Overview Of the Proposed Learning Methodsmentioning

confidence: 99%

“…The second process is applied at the time of the undesired output spike and consists of a reduction of the readout neuron weights that have spikes at the undesired output spike time or shortly before it by using anti-STDP similar to ReSuMe [25]. The third process reduces the readout neuron total PSP at the time of the undesired spike by adjusting the delays of the readout neuron based on EDL [43].…”

Section: A Overview Of the Proposed Learning 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%

“…The weights and delays of each output neuron are trained by EDL, as described in [43]. The delay adjustments in cooperation with the weight adjustments train an output neuron to increase its total PSP at a desired time to generate an actual output spike, and also the adjustments help the output neuron to reduce its PSP at undesired spike times and to remove undesired actual output spikes.…”

Section: B Training the Output Neuronsmentioning

confidence: 99%

“…x oh (t) is used to obtain appropriate value for delay adjustment. The adjustment ε oh is calculated by (4) similar to EDL [43]…”

Section: B Training the Output Neuronsmentioning

confidence: 99%

See 4 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: A Overview Of the Proposed Learning Methodsmentioning

confidence: 99%

Section: A Overview Of the Proposed Learning Methodsmentioning

confidence: 99%