TY - GEN
T1 - STORAGE OF SPARSE-CODED HETERO-ASSOCIATIONS WITH THE COMPETITIVE SYNAPTIC GROWTH NETWORK
AU - Bauer, Stephen
AU - Acharya, Raj
N1 - Publisher Copyright:
© 1992 IEEE.
PY - 1992
Y1 - 1992
N2 - In this paper we apply the Competitive Synaptic Growth Network(SGN) [11] to the storage and recall of sparse coded binary hetero-associations. The SGN is a two layer, feedforward neural network utilizing "complex"neurons having finite extent and "active"dendritic structures. The performance measure for the SGN is the number of connections needed to store noiseless sparse coded hetero-associations and perfectly recall these associations when given a perhaps noisy, input vector. Using the same number of network connections, the SGN clearly outperforms the benchmark Non-Holographic Associative Memory[8,9] (AM) applied to the same problem.
AB - In this paper we apply the Competitive Synaptic Growth Network(SGN) [11] to the storage and recall of sparse coded binary hetero-associations. The SGN is a two layer, feedforward neural network utilizing "complex"neurons having finite extent and "active"dendritic structures. The performance measure for the SGN is the number of connections needed to store noiseless sparse coded hetero-associations and perfectly recall these associations when given a perhaps noisy, input vector. Using the same number of network connections, the SGN clearly outperforms the benchmark Non-Holographic Associative Memory[8,9] (AM) applied to the same problem.
UR - https://www.scopus.com/pages/publications/85132025112
U2 - 10.1109/IJCNN.1992.287163
DO - 10.1109/IJCNN.1992.287163
M3 - Conference contribution
AN - SCOPUS:85132025112
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 499
EP - 504
BT - Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1992 International Joint Conference on Neural Networks, IJCNN 1992
Y2 - 7 June 1992 through 11 June 1992
ER -