Combining Feature Selection and Integration—A Neural Model for MT Motion Selectivity
نویسندگان
چکیده
منابع مشابه
Combining Feature Selection and Integration—A Neural Model for MT Motion Selectivity
BACKGROUND The computation of pattern motion in visual area MT based on motion input from area V1 has been investigated in many experiments and models attempting to replicate the main mechanisms. Two different core conceptual approaches were developed to explain the findings. In integrationist models the key mechanism to achieve pattern selectivity is the nonlinear integration of V1 motion acti...
متن کاملCombining Multiple Neural Nets for Visual Feature Selection and Classification
and lassi ation Gunther Heidemann and Helge Ritter AG Neuroinformatik, University of Bielefeld 33501 Bielefeld, Germany email: gheidema te hfak.uni-bielefeld.de De ember 15, 1999 Abstra t We present a system for obje t re ognition in real images employing three di erent types of neural networks, whi h a omplish feature extra tion and lassi ation. The main advantages of the method are its portab...
متن کاملCombining feature selection and feature reduction for protein classification
We use the n-grams descriptors for a protein classification task. As they are automatically generated, we obtain many irrelevant and/or redundant descriptors. In this paper, we evaluate various strategies of feature selection and feature reduction. First, we evaluate separately the efficiency of a filtering feature selection algorithm and a feature reduction on the basis of a singular value dec...
متن کاملCombining Feature Subsets in Feature Selection
In feature selection, a part of the features is chosen as a new feature subset, while the rest of the features is ignored. The neglected features still, however, may contain useful information for discriminating the data classes. To make use of this information, the combined classifier approach can be used. In our paper we study the efficiency of combining applied on top of feature selection/ex...
متن کاملCombining multiple classifiers for wrapper feature selection
Wrapper feature selection methods are widely used to select relevant features. However, wrappers only use a single classifier. The downside to this approach is that each classifier will have its own biases and will therefore select very different features. In order to overcome the biases of individual classifiers, this study introduces a new data mining method called wrapper-based decision tree...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: PLoS ONE
سال: 2011
ISSN: 1932-6203
DOI: 10.1371/journal.pone.0021254