| Kompare, B., 1995. The use of artificial intelligence in ecological modelling. Ph.D. Thesis, Royal Danish School of Pharmacy, Copenhagen, Denmark. |
....cases, some of the chemicals used in developing BIODEG also appear in our database and the correlation reported is not necessarily the same for unseen cases. We are currently investigating the exact extent of the overlap. Work on applying machine learning to predict biodegradability includes Kompare (1995), who compared several AI tools on the same domain and data and found these to yield better results than the classical statistical and probabilistic approaches, Zitko (1991) Cambon and Devillers (1993) who applied neural nets, and Gamberger et al. 1993) who applied several different approaches. ....
Kompare, B., 1995. The use of artificial intelligence in ecological modelling. Ph.D. Thesis, Royal Danish School of Pharmacy, Copenhagen, Denmark.
....In [11] CAS numbers for 144 of the 200 chemicals used to derive BIODEG are provided; of these, 21 also appear in our database. The correlation of BIODEG predictions is thus probably even lower than 0.6 for unseen cases. Work on applying machine learning to predict biodegradability includes [14], who compared several AI tools on the same domain and data and found these to yield better results than the classical statistical and probabilistic approaches, 23, 4] who applied neural nets, and [9] who applied several different approaches. 7 Conclusions and further work Predicting ....
Kompare, B. 1995. The use of artificial intelligence in ecological modelling. Ph.D. Thesis, Royal Danish School of Pharmacy, Copenhagen, Denmark.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC