ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2502.15829
29
0

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

20 February 2025
Christopher Johann Clarke
ArXivPDFHTML
Abstract

There has been difficulty utilising conditional statements as part of the neural network graph (e.g. if input >x> x>x, pass input to network NNN). 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.

View on arXiv
@article{clarke2025_2502.15829,
  title={ LACTOSE: Linear Array of Conditions, TOpologies with Separated Error-backpropagation -- The Differentiable "IF" Conditional for Differentiable Digital Signal Processing },
  author={ Christopher Johann Clarke },
  journal={arXiv preprint arXiv:2502.15829},
  year={ 2025 }
}
Comments on this paper