用类别分布预测事件，效果优于传统方法。
Categorical Distributions are Effective Neural Network Outputs for Event Prediction
- 将类别分布视为分段常数密度函数，建模连续时间事件
- 在多个数据集上表现优异，尤其适合小模型任务
- 设计新合成数据集，支持大模型测试与离散事件研究
我们证明了类别分布作为神经网络输出在预测下一个事件方面的有效性，适用于离散时间和连续时间事件序列。对于连续时间过程，类别分布被解释为分段常数密度函数，在多个数据集上表现出色。我们进一步强调研究离散时间过程的重要性，提出一种由视网膜假体启发的神经元尖峰预测任务，其事件时间自然离散化。此外，我们发现常用数据集倾向于偏好小型模型，并因此引入新的合成数据集用于测试更大模型，以及具有离散事件时间的合成数据集。
原文摘要 · Abstract (English)
We demonstrate the effectiveness of the categorical distribution as a neural network output for next event prediction. This is done for both discrete-time and continuous-time event sequences. To model continuous-time processes, the categorical distribution is interpreted as a piecewise-constant density function and is shown to be competitive across a range of datasets. We then argue for the importance of studying discrete-time processes by introducing a neuronal spike prediction task motivated by retinal prosthetics, where discretization of event times is consequent on the task description. Separately, we show evidence that commonly used datasets favour smaller models. Finally, we introduce new synthetic datasets for testing larger models, as well as synthetic datasets with discrete event times.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。