让神经网络的if条件可微分，实现条件化模型切换。
LACTOSE: Linear Array of Conditions, TOpologies with Separated Error-backpropagation -- The Differentiable "IF" Conditional for Differentiable Digital Signal Processing
- 将条件分支拆解为可反向传播的线性结构，突破传统if不可导瓶颈。
- 按输入范围动态加载对应参数，在推理时实现条件选择。
- 适合需要条件化处理的信号建模任务，如音频合成与数字信号处理。
传统神经网络难以在图中使用条件语句（如：若输入 > x，将输入传递给网络 N），原因在于分支条件无法反向传播梯度。本文提出的LACTOSE算法解决了这一问题，使条件化使用机器学习层成为可能。该算法通过为用户定义的数值区间存储训练参数，并在预测时动态加载，实现了条件分支的可微计算。研究以简单版DDSP为例，重点在于构建适用于DDSP的可微分‘if’条件机制。
原文摘要 · Abstract (English)
There has been difficulty utilising conditional statements as part of the neural network graph (e.g. if input $> x$, pass input to network $N$). This is due to the inability to backpropagate through branching conditions. The Linear Array of Conditions, TOpologies with Separated Error-backpropagation (LACTOSE) Algorithm addresses this issue and allows the conditional use of available machine learning layers for supervised learning models. In this paper, the LACTOSE algorithm is applied to a simple use of DDSP, however, the main point is the development of the "if" conditional for DDSP use. The LACTOSE algorithm stores trained parameters for each user-specified numerical range and loads the parameters dynamically during prediction.
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。