Event-based cameras record an asynchronous stream of per-pixel brightness changes. As such, they have numerous advantages over the standard frame-based cameras, including high temporal resolution, high dynamic range, and no motion blur. Due to the asynchronous nature, efficient learning of compact representation for event data is challenging. While it remains not explored the extent to which the spatial and temporal event "information" is useful for pattern recognition tasks. In this paper, we focus on single-layer architectures. We analyze the performance of two general problem formulations: the direct and the inverse, for unsupervised feature learning from local event data (local volumes of events described in space-time). We identify and show the main advantages of each approach. Theoretically, we analyze guarantees for an optimal solution, possibility for asynchronous, parallel parameter update, and the computational complexity. We present numerical experiments for object recognition. We evaluate the solution under the direct and the inverse problem and give a comparison with the state-of-the-art methods. Our empirical results highlight the advantages of both approaches for representation learning from event data. We show improvements of up to 9 % in the recognition accuracy compared to the state-of-the-art methods from the same class of methods.

中文翻译：

---

事件数据的无监督特征学习：直接与逆向问题公式化

基于事件的相机记录每像素亮度变化的异步流。因此，与标准的基于帧的相机相比，它们具有许多优势，包括高时间分辨率、高动态范围和无运动模糊。由于异步性质，事件数据的紧凑表示的有效学习具有挑战性。虽然它仍然没有探索空间和时间事件“信息”对模式识别任务有用的程度。在本文中，我们专注于单层架构。我们分析了两个一般问题公式的性能：直接和逆，用于从局部事件数据（在时空描述的局部事件量）中进行无监督特征学习。我们确定并展示了每种方法的主要优点。理论上，我们分析了最佳解决方案的保证、异步、并行参数更新的可能性以及计算复杂性。我们提出了用于物体识别的数值实验。我们评估了正问题和逆问题下的解决方案，并与最先进的方法进行了比较。我们的实证结果突出了两种从事件数据中学习表征的方法的优势。与同类方法的最新方法相比，我们的识别准确度提高了 9%。我们的实证结果突出了两种从事件数据中学习表征的方法的优势。与同类方法的最新方法相比，我们的识别准确度提高了 9%。我们的实证结果突出了两种从事件数据中学习表征的方法的优势。与同类方法的最新方法相比，我们的识别准确度提高了 9%。