# LACTOSE: Linear Array of Conditions, TOpologies with Separated Error-backpropagation -- The Differentiable "IF" Conditional for Differentiable Digital Signal Processing

arXiv: https://arxiv.org/abs/2502.15829 · HTML: https://mlsanity.com/paper/2502.15829/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 19 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Builds on (most cited first, 5 of 5)

- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Features](https://mlsanity.com/paper/1907.01749/) (2019)
- [A Conditional Splitting Framework for Efficient Constituency Parsing](https://mlsanity.com/paper/2106.15760/) (2021)
- [DeepDrum: An Adaptive Conditional Neural Network](https://mlsanity.com/paper/1809.06127/) (2018)
- [Class-Conditional VAE-GAN for Local-Ancestry Simulation](https://mlsanity.com/paper/1911.13220/) (2019)

## Abstract (arXiv)

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.