Effective AER Object Classification Using Segmented Probability-Maximization Learning in Spiking Neural Networks
This work addresses the problem of efficient learning for AER object classification in SNNs, which is incremental as it builds on existing methods with a novel algorithm.
The paper tackles the challenge of object classification with address event representation (AER) cameras using spiking neural networks (SNNs) by proposing a segmented probability-maximization (SPA) learning algorithm, which improves reliability and effectiveness, resulting in higher accuracy with less information compared to state-of-the-art methods.
Address event representation (AER) cameras have recently attracted more attention due to the advantages of high temporal resolution and low power consumption, compared with traditional frame-based cameras. Since AER cameras record the visual input as asynchronous discrete events, they are inherently suitable to coordinate with the spiking neural network (SNN), which is biologically plausible and energy-efficient on neuromorphic hardware. However, using SNN to perform the AER object classification is still challenging, due to the lack of effective learning algorithms for this new representation. To tackle this issue, we propose an AER object classification model using a novel segmented probability-maximization (SPA) learning algorithm. Technically, 1) the SPA learning algorithm iteratively maximizes the probability of the classes that samples belong to, in order to improve the reliability of neuron responses and effectiveness of learning; 2) a peak detection (PD) mechanism is introduced in SPA to locate informative time points segment by segment, based on which information within the whole event stream can be fully utilized by the learning. Extensive experimental results show that, compared to state-of-the-art methods, not only our model is more effective, but also it requires less information to reach a certain level of accuracy.