F
Frank R. Burden
Researcher at Commonwealth Scientific and Industrial Research Organisation
Publications - 67
Citations - 3796
Frank R. Burden is an academic researcher from Commonwealth Scientific and Industrial Research Organisation. The author has contributed to research in topics: Artificial neural network & Quantitative structure–activity relationship. The author has an hindex of 30, co-authored 67 publications receiving 3352 citations. Previous affiliations of Frank R. Burden include Flinders University & Monash University.
Papers
More filters
Journal ArticleDOI
Robust QSAR Models from Novel Descriptors and Bayesian Regularised Neural Networks
David A. Winkler,Frank R. Burden +1 more
TL;DR: A specific type of neural network is used, the Bayesian Regularized Artificial Neural Network (BRANN), in the development of SAR models, which have the potential to solve a number of problems which arise in QSAR modelling such as: choice of model; robustness of model%; choice of validation set; size of validation effort; and optimization of network architecture.
Journal ArticleDOI
Molecular Identification Number for Substructure Searches.
TL;DR: In this article, a method for producing molecular identification numbers for hydrogen-depleted organic structures from the eigenvalues of a connectivity matrix is presented, and the method can also be used to identify which atoms belong to each of the substructures of a disconnected main structure.
Journal Article
Infrared microspectroscopy and artificial neural networks in the diagnosis of cervical cancer.
TL;DR: Infrared spectra of 88 normal and 32 abnormal cervical smear samples were used as a databank to investigate the usefulness of artificial neural networks in the diagnosis of cervical smears and indicate that neural networks coupled to infrared microspectroscopy could provide an alternative automated means of screening for cervical cancer.
Journal ArticleDOI
Relevance Vector Machines: Sparse Classification Methods for QSAR
Frank R. Burden,David A. Winkler +1 more
TL;DR: It is shown that RVM models are substantially sparser than the SVM models and have similar or superior performance to them.
Journal ArticleDOI
Using Artificial Neural Networks to Predict Biological Activity from Simple Molecular Structural Considerations
TL;DR: It is concluded that neural networks can be used to predict biological activity, within a series of closely related molecules, from molecular structural considerations alone so saving much effort in synthesis and in vivo testing with new candidate molecules.