Exploiting the potential of deep reinforcement learning for classification tasks in high-dimensional and unstructured data

This paper presents a framework for efficiently learning feature selection policies which use less features to reach a high classification precision on large unstructured data. It uses a Deep Convolutional Autoencoder (DCAE) for learning compact feature spaces, in combination with recently-proposed...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Obando-Ceron, Johan S, Cano, Victor Romero, Toro, Walter Mayor
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper presents a framework for efficiently learning feature selection policies which use less features to reach a high classification precision on large unstructured data. It uses a Deep Convolutional Autoencoder (DCAE) for learning compact feature spaces, in combination with recently-proposed Reinforcement Learning (RL) algorithms as Double DQN and Retrace.
DOI:10.48550/arxiv.1912.09595