4 papers
Busemann energy-based attention for emotion analysis in Poincaré discs
Zinaid KapiÄ, Vladimir JaÄimoviÄ
We present EmBolic - a novel fully hyperbolic deep learning architecture for fine-grained emotion analysis from textual messages. The underlying idea is that hyperbolic geometry ef…
Clustering in hyperbolic balls
Vladimir JaÄimoviÄ, Aladin CrnkiÄ
The idea of representations of the data in negatively curved manifolds recently attracted a lot of attention and gave a rise to the new research direction named {\it hyperbolic mac…
A group-theoretic framework for machine learning in hyperbolic spaces
Vladimir JaÄimoviÄ
Embedding the data in hyperbolic spaces can preserve complex relationships in very few dimensions, thus enabling compact models and improving efficiency of machine learning (ML) al…
Reinforcement Learning in Hyperbolic Spaces: Models and Experiments
Vladimir JaÄimoviÄ, Zinaid KapiÄ, Aladin CrnkiÄ
We examine five setups where an agent (or two agents) seeks to explore unknown environment without any prior information. Although seemingly very different, all of them can be form…