GitHub

Testing-Linear-Separability-between-Two-Sets-in-any-dimension-python

This project is the Python reference implementation of the linear separability testing algorithm proposed in: Shuiming Zhong and Huan Lyu, "A New Sufficient & Necessary Condition for Testing Linear ...
GitHub

A tiny reproduction of "Denoising Diffusion Autoencoders are Unified Self-supervised Learners." Verifies emergent linear separability in lightweight models on CIFAR-10.

The goal of this project is to verify the scale-invariance of the DDAE hypothesis: that diffusion models inherently learn linearly separable, semantic representations within their intermediate layers, ...
IEEE

Preserving Linear Separability in Continual Learning by Backward Feature Projection

Abstract: Catastrophic forgetting has been a major challenge in continual learning, where the model needs to learn new tasks with limited or no access to data from previously seen tasks. To tackle ...
IEEE

Testing linear separability in classification of inflection rules

Abstract: Agglutinative languages, such as Hungarian, use inflection to modify the meaning of words. Inflection is a string transformation which describe how can a word converted into its inflected ...