LACTOSE: Linear Array of Conditions, TOpologies with Separated Error-backpropagation -- The Differentiable "IF" Conditional for Differentiable Digital Signal Processing
This addresses a specific technical bottleneck in machine learning for researchers and practitioners working with conditional logic in neural networks, though it appears incremental as it builds on existing DDSP methods.
The paper tackles the problem of incorporating conditional statements into neural network graphs, which is hindered by the inability to backpropagate through branching conditions, and introduces the LACTOSE algorithm to enable differentiable 'if' conditionals for supervised learning models, applied to differentiable digital signal processing (DDSP).
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.