Abstract
There has been a lot of research on supervised learning in spiking neural network (SNN) for a couple of decades to improve computational efficiency. However, evolutionary algorithm based supervised learning for SNN has not been investigated thoroughly which is still in embryo stage. This paper introduce an efficient algorithm (SpiFoG) to train multilayer feed forward SNN in supervised manner that uses elitist floating point genetic algorithm with hybrid crossover. The evidence from neuroscience claims that the brain uses spike times with random synaptic delays for information processing. Therefore, leaky-integrate-and-fire spiking neuron is used in this research introducing random synaptic delays. The SpiFoG allows both excitatory and inhibitory neurons by allowing a mixture of positive and negative synaptic weights. In addition, random synaptic delays are also trained with synaptic weights in an efficient manner. Moreover, computational efficiency of SpiFoG was increased by reducing the total simulation time and increasing the time step since increasing time step within the total simulation time takes less iteration. The SpiFoG is benchmarked on Iris and WBC dataset drawn from the UCI machine learning repository and found better performance than state-of-the-art techniques.
Highlights
There has been a lot of research on supervised learning in spiking neural network (SNN) for a couple of decades to improve computational efficiency
SpiFoG is benchmarked against the Iris and WBC dataset drawn from the UCI machine learning repository
This paper proposed SpiFoG algorithm to train multilayer feed forward SNN
Summary
There has been a lot of research on supervised learning in spiking neural network (SNN) for a couple of decades to improve computational efficiency. Sporea et al.[21] had used spike time dependent plasticity (STDP) and anti-STDP to device more similar biological supervised learning for multilayer SNN This method allows neuron in all the layers to fire multiple times. In29, a supervised training algorithm is proposed where a neuron learns spike timing-based decisions called tempotron which allows neurons to learn whether to fire or not in response to a particular input stimuli. Due to the lack of efficient supervised learning algorithm and difficulty in software implementation, SNN became less popular it is energy efficient, provides good computational power and biologically plausible. (1) An efficient supervised learning algorithm (SpiFoG) for multilayer feed-forward SNN is proposed. (2) Random delays are introduced in the synapse model of LIF neuron which are trained with synaptic weights. (3) Both positive and negative values are allowed to add more biological plausibility to the system. (4) The total simulation time is reduced, and the value of time step is increased to improve computational efficiency. (5) Hybrid crossover method is used for the faster convergence providing well exploration of the search space
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
