Unsupervised learning of perceptual feature combinations.

Autor: Minija Tamosiunaite, Christian Tetzlaff, Florentin Wörgötter
Jazyk: angličtina
Rok vydání: 2024
Předmět:
Zdroj: PLoS Computational Biology, Vol 20, Iss 3, p e1011926 (2024)
Druh dokumentu: article
ISSN: 1553-734X
1553-7358
DOI: 10.1371/journal.pcbi.1011926
Popis: In many situations it is behaviorally relevant for an animal to respond to co-occurrences of perceptual, possibly polymodal features, while these features alone may have no importance. Thus, it is crucial for animals to learn such feature combinations in spite of the fact that they may occur with variable intensity and occurrence frequency. Here, we present a novel unsupervised learning mechanism that is largely independent of these contingencies and allows neurons in a network to achieve specificity for different feature combinations. This is achieved by a novel correlation-based (Hebbian) learning rule, which allows for linear weight growth and which is combined with a mechanism for gradually reducing the learning rate as soon as the neuron's response becomes feature combination specific. In a set of control experiments, we show that other existing advanced learning rules cannot satisfactorily form ordered multi-feature representations. In addition, we show that networks, which use this type of learning always stabilize and converge to subsets of neurons with different feature-combination specificity. Neurons with this property may, thus, serve as an initial stage for the processing of ecologically relevant real world situations for an animal.
Databáze: Directory of Open Access Journals
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje