PRIMENA METRIČKOG UČENJA U POLJOPRIVREDI
Ključne reči:
Metričko učenje, mašinsko učenje, poljoprivreda
Apstrakt
U ovom radu prikazujemo primenu metričkog učenja i mogućnost lakog skaliranja na nove klase bez potrebe za ponovnim obučavanjem u oblasti poljoprivrede, na klasifikaciji vrste cveća, vrste lista biljaka i bolesti lista biljaka.
Reference
[1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun: Deep Residual Learning for Image Recognition, Microsoft Research, arXiv:1512.03385, 2015.
[2] Leslie N. Smith: Cyclical Learning Rates for Training Neural Networks, U.S. Naval Research Laboratory, arXiv: 1506.01186, 2017.
[3] Xun Wang, Xintong Han, Weilin Huang∗, Dengke Dong, Matthew R. Scott: Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning, Malong Technologies, Shenzhen, China, arXiv: 1904.06627, 2022
[4] Eric P. Xing, Andrew Y. Ng, Michael I. Jordan, and Stuart J. Russell: Distance Metric Learning with Application to Clustering with Side-Information, Advances in Neural Information Processing Systems (NIPS) 15, pages 505–512, 2002.
[2] Leslie N. Smith: Cyclical Learning Rates for Training Neural Networks, U.S. Naval Research Laboratory, arXiv: 1506.01186, 2017.
[3] Xun Wang, Xintong Han, Weilin Huang∗, Dengke Dong, Matthew R. Scott: Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning, Malong Technologies, Shenzhen, China, arXiv: 1904.06627, 2022
[4] Eric P. Xing, Andrew Y. Ng, Michael I. Jordan, and Stuart J. Russell: Distance Metric Learning with Application to Clustering with Side-Information, Advances in Neural Information Processing Systems (NIPS) 15, pages 505–512, 2002.
Objavljeno
2023-01-08
Sekcija
Elektrotehničko i računarsko inženjerstvo
