Convolutional Spike Timing Dependent Plasticity based Feature Learning in Spiking Neural Networks
This work addresses efficient and biologically plausible learning for neuromorphic applications, though it appears incremental as it builds on existing SNN architectures.
The authors tackled feature learning in spiking neural networks by proposing a convolutional spike timing dependent plasticity method, which improved sparsity and robustness, achieving competitive accuracy in object recognition with fewer examples and enabling out-of-set generalization.
Brain-inspired learning models attempt to mimic the cortical architecture and computations performed in the neurons and synapses constituting the human brain to achieve its efficiency in cognitive tasks. In this work, we present convolutional spike timing dependent plasticity based feature learning with biologically plausible leaky-integrate-and-fire neurons in Spiking Neural Networks (SNNs). We use shared weight kernels that are trained to encode representative features underlying the input patterns thereby improving the sparsity as well as the robustness of the learning model. We demonstrate that the proposed unsupervised learning methodology learns several visual categories for object recognition with fewer number of examples and outperforms traditional fully-connected SNN architectures while yielding competitive accuracy. Additionally, we observe that the learning model performs out-of-set generalization further making the proposed biologically plausible framework a viable and efficient architecture for future neuromorphic applications.