Abstract
Spiking Neural Networks (SNNs) are fast becoming a promising candidate for brain-inspired neuromorphic computing because of their inherent power efficiency and impressive inference accuracy across several cognitive tasks such as image classification and speech recognition. The recent efforts in SNNs have been focused on implementing deeper networks with multiple hidden layers to incorporate exponentially more difficult functional representations. In this paper, we propose a pre-training scheme using biologically plausible unsupervised learning, namely Spike-Timing-Dependent-Plasticity (STDP), in order to better initialize the parameters in multi-layer systems prior to supervised optimization. The multi-layer SNN is comprised of alternating convolutional and pooling layers followed by fully-connected layers, which are populated with leaky integrate-and-fire spiking neurons. We train the deep SNNs in two phases wherein, first, convolutional kernels are pre-trained in a layer-wise manner with unsupervised learning followed by fine-tuning the synaptic weights with spike-based supervised gradient descent backpropagation. Our experiments on digit recognition demonstrate that the STDP-based pre-training with gradient-based optimization provides improved robustness, faster (~2.5 ×) training time and better generalization compared with purely gradient-based training without pre-training.
Highlights
In this era of data deluge with real-time content continuously generated by distributed sensors, intelligent neuromorphic systems are required to efficiently deal with the massive amount of data and computations in ubiquitous automobiles and portable edge devices
The privacy issues can not be overlooked in case of disclosing, sharing and destroying the personal data generated from edge devices for Artificial Neural Network (ANN) training in cloud services
Recent efforts in spiking neural networks have been focused toward building multi-layer systems to hierarchically represent highly nonlinear and complex functions
Summary
In this era of data deluge with real-time content continuously generated by distributed sensors, intelligent neuromorphic systems are required to efficiently deal with the massive amount of data and computations in ubiquitous automobiles and portable edge devices. Spiking Neural Networks (SNNs), often regarded as third generation brain-inspired neural networks (Maass, 1997), can be highly power-efficient and have competitive capabilities to deal with several cognitive tasks (Khan et al, 2008; Jo et al, 2010; Merolla et al, 2014). STDP-Based Pre-training and recognition tasks (Brader et al, 2007; Diehl and Cook, 2015; Zhao et al, 2015). They necessitate large number of trainable parameters to attain competitive classification accuracy, which constrains their scalability for complex applications. The training of deep SNNs remains an intricate and challenging problem
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
