Scholars' Mine
Missouri S&T
Research Repository
Curtis Laws Wilson Library
400 W. 14th Street
Rolla, MO 65409-0060
scholarsmine@mst.edu
| Title: | Generalization of features in the assembly neural networks |
| Author (s): | Goltsev, Alexander. Wunsch, Donald C. |
| Department/Lab Affiliations: | Applied Computational Intelligence Laboratory Electrical and Computer Engineering |
| Keywords: | Neural assembly Neuron excitatory binary connection generation neural column recognition sub-network |
| Issue Date: | 2004 |
| Publisher: | World Scientific Publishing |
| Citation: | Goltsev, Alexander., and Donald C. Wunsch. "Generalization of Features in the Assembly Neural Networks." International Journal of Neural Systems, 14, (2004). |
| Abstract: | The purpose of the paper is an experimental study of the formation of class descriptions, taking place during learning, in assembly neural networks. The assembly neural network is artificially partitioned into several sub-networks according to the number of classes that the network has to recognize. The features extracted from input data are represented in neural column structures of the sub-networks. Hebbian neural assemblies are formed in the column structure of the sub-networks by weight adaptation. A specific class description is formed in each sub-network of the assembly neural network due to intersections between the neural assemblies. The process of formation of class descriptions in the sub-networks is interpreted as feature generalization. A set of special experiments is performed to study this process, on a task of character recognition using the MNIST database. |
| Type: | Article - Journal text |
| In Title: | International Journal of Neural Systems |
| Copyright Notice: | This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. FULL COPYRIGHT INFORMATION: |
| Link to this page: |
| title | Generalization of features in the assembly neural networks |
| contributor.author | Goltsev, Alexander. |
| contributor.author | Wunsch, Donald C. |
| contributor.deptlab | Applied Computational Intelligence Laboratory |
| contributor.deptlab | Electrical and Computer Engineering |
| subject | Neural assembly |
| subject | Neuron |
| subject | excitatory binary connection |
| subject | generation |
| subject | neural column |
| subject | recognition |
| subject | sub-network |
| date.issued | 2004 |
| publisher | World Scientific Publishing |
| identifier.citation | Goltsev, Alexander., and Donald C. Wunsch. "Generalization of Features in the Assembly Neural Networks." International Journal of Neural Systems, 14, (2004). |
| description.abstract | The purpose of the paper is an experimental study of the formation of class descriptions, taking place during learning, in assembly neural networks. The assembly neural network is artificially partitioned into several sub-networks according to the number of classes that the network has to recognize. The features extracted from input data are represented in neural column structures of the sub-networks. Hebbian neural assemblies are formed in the column structure of the sub-networks by weight adaptation. A specific class description is formed in each sub-network of the assembly neural network due to intersections between the neural assemblies. The process of formation of class descriptions in the sub-networks is interpreted as feature generalization. A set of special experiments is performed to study this process, on a task of character recognition using the MNIST database. |
| type | Article - Journal |
| type.DCMIType | text |
| type.status | Final version |
| rights | This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. |
| rights.URI | |
| relation.isPartOf | International Journal of Neural Systems |
| date.accessioned | 2007-04-11T17:00:48Z |
| date.available | 2008-03-20T16:27:45Z |
| identifier.persist.URI |