no code implementations • 13 Feb 2024 • Heinrich van Deventer, Anna Sergeevna Bosman
Continual learning is the sequential learning of different tasks by a machine learning model.
no code implementations • 14 Feb 2023 • Thamsanqa Mlotshwa, Heinrich van Deventer, Anna Sergeevna Bosman
In supervised machine learning, the choice of loss function implicitly assumes a particular noise distribution over the data.
no code implementations • 10 Aug 2022 • Heinrich van Deventer, Anna Bosman
Furthermore, we present ATLAS: a novel ANN architecture based on the new theorem.
1 code implementation • 12 May 2022 • Heinrich van Deventer, Pieter Janse van Rensburg, Anna Bosman
SAM is extended with the Kolmogorov-Arnold representation theorem to a novel universal function approximator, called the Kolmogorov-Arnold Spline Additive Model - KASAM.