A discourse delivered on Thanksgiving Day, Dec. 7, 1837 : in the Unitarian Church, Keene, N.H.

The print copy of this sermon is held by Pitts Theology Library. The Pitts Theology Library's digital copy was produced as part of the ATLA/ATS Cooperative Digital Resources Initiative (CDRI), funded by the Luce Foundation. Electronic reproduction. Atlanta, Georgia : Pitts Theology Library, Emory University, 2003. (Thanksgiving Day Sermons, ATLA Cooperative Digital Resources Initiative, CDRI). Joint CDRI project by: Andover-Harvard Library (Harvard Divinity School), Pitts Theology Library (Emory University), and Princeton Theological Seminary Libraries.

True Greatness: A Discourse on the character of Rev. Wilbur Fisk

Memorial discourse

The universal mission of the church of Christ : a discourse / delivered at Hanley, Staffordshire, August 4, 1884, being the Fernley lecture of 1884, by Benjamin Hellier.

http://www.archive.org/details/universalmission00helluoft

By the equator's snowy peak a record of medical missionary work and travel in British East Africa by E May Crawford

http://www.archive.org/details/equatorssnowype00crawuoft

How far to the nearest doctor? Stories of medical missions around the world, by Edward M. Dodd.

http://www.archive.org/details/howfartotheneare012020mbp

Rule Extraction, Fuzzy ARTMAP, and Medical Databases

This paper shows how knowledge, in the form of fuzzy rules, can be derived from a self-organizing supervised learning neural network called fuzzy ARTMAP. Rule extraction proceeds in two stages: pruning removes those recognition nodes whose confidence index falls below a selected threshold; and quantization of continuous learned weights allows the final system state to be translated into a usable set of rules. Simulations on a medical prediction problem, the Pima Indian Diabetes (PID) database, illustrate the method. In the simulations, pruned networks about 1/3 the size of the original actually show improved performance. Quantization yields comprehensible rules with only slight degradation in test set prediction performance.