Hierarchical Learning of Dependent Concepts for Human Activity Recognition
| Autor: | Pegah Alizadeh, Aomar Osmani, Massinissa Hamidi |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Exponential complexity
Hierarchy Process (engineering) business.industry Computer science 02 engineering and technology Machine learning computer.software_genre Class (biology) Separable space Reduction (complexity) Activity recognition 020204 information systems 0202 electrical engineering electronic engineering information engineering Natural (music) 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Zdroj: | Advances in Knowledge Discovery and Data Mining ISBN: 9783030757649 PAKDD (2) |
| DOI: | 10.1007/978-3-030-75765-6_7 |
| Popis: | In multi-class classification tasks, like human activity recognition, it is often assumed that classes are separable. In real applications, this assumption becomes strong and generates inconsistencies. Besides, the most commonly used approach is to learn classes one-by-one against the others. This computational simplification principle introduces strong inductive biases on the learned theories. In fact, the natural connections among some classes, and not others, deserve to be taken into account. In this paper, we show that the organization of overlapping classes (multiple inheritances) into hierarchies considerably improves classification performances. This is particularly true in the case of activity recognition tasks featured in the SHL dataset. After theoretically showing the exponential complexity of possible class hierarchies, we propose an approach based on transfer affinity among the classes to determine an optimal hierarchy for the learning process. Extensive experiments show improved performances and a reduction in the number of examples needed to learn. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|