Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditional Feature Learning Approaches?

Abstract

Spiking neural networks (SNNs) equipped with latency coding and spike-timing dependent plasticity rules offer an alternative to solve the data and energy bottlenecks of standard computer vision approaches: they can learn visual features without supervision and can be implemented by ultra-low power hardware architectures. However, their performance in image classification has never been evaluated on recent image datasets. In this paper, we compare SNNs to auto-encoders on three visual recognition datasets, and extend the use of SNNs to color images. The analysis of the results helps us identify some bottlenecks of SNNs: the limits of on-center/off-center coding, especially for color images, and the ineffectiveness of current inhibition mechanisms. These issues should be addressed to build effective SNNs for image recognition.

References in corpus (7)

• ADADELTA: An Adaptive Learning Rate Method
• Deep Learning in Spiking Neural Networks
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing
• STDP-based spiking deep convolutional neural networks for object recognition
• First-spike based visual categorization using reward-modulated STDP
• Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition

Cited by in corpus (11)

• Photonic spiking neural networks and CMOS-compatible graphene-on-silicon spiking neurons
• Parallel Hyperparameter Optimization Of Spiking Neural Network
• LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing
• Paired Competing Neurons Improving STDP Supervised Local Learning In Spiking Neural Networks
• A Study On the Effects of Pre-processing On Spatio-temporal Action Recognition Using Spiking Neural Networks Trained with STDP
• Improving STDP-based Visual Feature Learning with Whitening
• Generative Adversarial Networks And Domain Adaptation For Training Data Independent Image Registration
• Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition
• S3TC: Spiking Separated Spatial and Temporal Convolutions with Unsupervised STDP-based Learning for Action Recognition
• SPA: Stochastic Probability Adjustment for System Balance of Unsupervised SNNs
• Mining atmospheric data