5 papers
Identifiability of Deep Polynomial Neural Networks
Konstantin Usevich, Ricardo Borsoi, Clara Dérand +1
Polynomial Neural Networks (PNNs) possess a rich algebraic and geometric structure. However, their identifiability -- a key property for ensuring interpretability -- remains poorly…
Low-Rank Tensor Decompositions for the Theory of Neural Networks
Ricardo Borsoi, Konstantin Usevich, Marianne Clausel
The groundbreaking performance of deep neural networks (NNs) promoted a surge of interest in providing a mathematical basis to deep learning theory. Low-rank tensor decompositions…
Coupled tensor models for probability mass function estimation: Part II, Uniqueness of the model
Philippe Flores, Konstantin Usevich, David Brie
In this paper, uniqueness properties of a coupled tensor model are studied. This new coupled tensor model is used in a new method called Partial Coupled Tensor Factorization of 3D…
Coupled tensor models for probability mass function estimation: Part I, Principles and algorithms
Philippe Flores, Konstantin Usevich, David Brie
In this article, a Probability Mass Function (PMF) estimation method which tames the curse of dimensionality is proposed. This method, called Partial Coupled Tensor Factorization o…
Personalized Coupled Tensor Decomposition for Multimodal Data Fusion: Uniqueness and Algorithms
Ricardo Augusto Borsoi, Konstantin Usevich, David Brie +1
Coupled tensor decompositions (CTDs) perform data fusion by linking factors from different datasets. Although many CTDs have been already proposed, current works do not address imp…