Mapping the Research Landscape of Deep Learning from 2001 to 2019
International Informatics and Software Engineering Conference (UBMYK), Ankara, Türkiye, 6 - 07 Kasım 2019, ss.1-5, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/ubmyk48245.2019.8965595
- Basıldığı Şehir: Ankara
- Basıldığı Ülke: Türkiye
- Sayfa Sayıları: ss.1-5
- Karadeniz Teknik Üniversitesi Adresli: Evet
Özet
This paper analyzes recent literature to investigate the emerging topics and trends in deep learning research. A semantic content analysis based on probabilistic topic modeling was performed on 22,279 journal articles on deep learning published between 2001 and 2019. The analysis revealed 18 topics mapping the research landscape of the field. Classification has the highest ratio (10.57%), followed by Image feature representing (8.90%) and Data applications (8.71%). Using the time-dependent average and acceleration of each topic, the topics were further separated into hot topics, stable topics and cold topics.