#### Filter Results:

- Full text PDF available (1)

#### Publication Year

1987

2011

- This year (0)
- Last 5 years (0)
- Last 10 years (1)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

Learn More

- Edward M. Corwin, Antonette M. Logar, William J. B. Oldham
- IEEE Trans. Neural Networks
- 1994

Concerns the problem of finding weights for feed-forward networks in which threshold functions replace the more common logistic node output function. The advantage of such weights is that the complexity of the hardware implementation of such networks is greatly reduced. If the task to be learned does not change over time, it may be sufficient to find the… (More)

- Enkhsaikhan Boldsaikhan, Edward M. Corwin, Antonette M. Logar, William J. Arbegast
- Appl. Soft Comput.
- 2011

Find the secret to improve the quality of life by reading this assembly language programming for the 68000. This is a kind of book that you need now. Besides, it can be your favorite book to read after having this book. Do you ask why? Well, this is a book that has different characteristic with others. You may not need to know who the author is, how… (More)

We describe a massively parallel implementation of genetic algorithms using a MasPar MP-1 data-parallel computer. Modification of the sequential genetic algorithm required that several important issues be addressed, in particular how to implement the selection operator with a minimum of inter-processor communication. A speed up of at least 145 times… (More)

- Manuel L. Penaloza, Antonette M. Logar, Joseph Johnson, Michael Boucher
- Computers and Their Applications
- 2001

- Antonette M. Logar, David E. Lloyd, +5 authors Ronald Welch
- IEEE Trans. Geoscience and Remote Sensing
- 1998

- Antonette M. Logar, Edward M. Corwin, William J. B. Oldham
- Int. J. Hum.-Comput. Stud.
- 1994

This paper explores the application of neural networks, specificallyback propagation networks, to the problem of predicting the acid concentration of WasteWater. Experiments were conducted to determine the effects of varyingnetwork parameters such as the size of the tag, the normalization technique, and the number of steps forward in time the network is… (More)

The technique of using pairwise linear discriminants for pattern classification is extended here to produce a training algorithm for a multi-layer perceptron network. The result is a neural network which finds pairwise non-linear separating surfaces. The training algorithqa is analogous to a method for simplifying combinatorial circuits, that is, for any… (More)

- Edward M. Corwin, Antonette M. Logar, William J. B. Oldham
- Neurocomputing
- 1998

- ‹
- 1
- ›