Larry M. Manevitz

NeSy Conference 2007 Conference Paper

Using Neural Network Models to Model Cerebral Hemispheric Differences in Processing Ambiguous Words

• Orna Peleg
• Zohar Eviatar
• Larry M. Manevitz
• Hananel Hazan

Neuropsychological studies have shown that both cerebral hemispheres process orthographic, phonological and semantic aspects of written words, albeit in different ways. The Left Hemisphere (LH) is more influenced by the phonological aspect of written words whereas lexical processing in the Right Hemisphere (RH) is more sensitive to visual form. We explain this phenomenon by postulating that in the Left Hemisphere (LH) orthography, phonology and semantics are interconnected while in the Right Hemisphere (RH), phonology is not connected directly to orthography and hence its influence must be mitigated by semantical processing. We test this hypothesis by complementary human psychophysical experiments and by dual (one RH and one LH) computational neural network model architecturally modified from Kowamoto's [1993] model to follow our hypothesis. In this paper we present the results of the computational model and show that the results obtained are analogous to the human experiments.

JMLR Journal 2001 Journal Article

One-Class SVMs for Document Classification (Kernel Machines Section)

• Larry M. Manevitz
• Malik Yousef

We implemented versions of the SVM appropriate for one-class classification in the context of information retrieval. The experiments were conducted on the standard Reuters data set. For the SVM implementation we used both a version of Schoelkopf et al. and a somewhat different version of one-class SVM based on identifying "outlier" data as representative of the second-class. We report on experiments with different kernels for both of these implementations and with different representations of the data, including binary vectors, tf-idf representation and a modification called "Hadamard" representation. Then we compared it with one-class versions of the algorithms prototype (Rocchio), nearest neighbor, naive Bayes, and finally a natural one-class neural network classification method based on "bottleneck" compression generated filters. The SVM approach as represented by Schoelkopf was superior to all the methods except the neural network one, where it was, although occasionally worse, essentially comparable. However, the SVM methods turned out to be quite sensitive to the choice of representation and kernel in ways which are not well understood; therefore, for the time being leaving the neural network approach as the most robust.

IJCAI Conference 1987 Conference Paper

Combining Bodies of Dependent Information

• Robert Hummel
• Larry M. Manevitz