TY - GEN

T1 - Dynamic programming algorithm for training functional networks

AU - El-Sebakhy, Emad A.

AU - Mohammed, Salahadin A.

AU - Elshafei, Moustafa A.

PY - 2007

Y1 - 2007

N2 - The paper proposes a dynamic programming algorithm for training of functional networks. The algorithm considers each node as a state. The problem is formulated as finding the sequence of states which minimizes the sum of the squared errors approximation. Each node is optimized with regard to its corresponding neural functions and its estimated neuron functions. The dynamic programming algorithm tries to find the best path from the final layer nodes to the input layer which minimizes an optimization criterion. Finally, in the pruning stage, the unused nodes are deleted. The output layer can be taken as a summation node using some linearly independent families, such as, polynomial, exponential, Fourier, etc. The algorithm is demonstrated by two examples and compared with other common algorithms in both computer science and statistics communities.

AB - The paper proposes a dynamic programming algorithm for training of functional networks. The algorithm considers each node as a state. The problem is formulated as finding the sequence of states which minimizes the sum of the squared errors approximation. Each node is optimized with regard to its corresponding neural functions and its estimated neuron functions. The dynamic programming algorithm tries to find the best path from the final layer nodes to the input layer which minimizes an optimization criterion. Finally, in the pruning stage, the unused nodes are deleted. The output layer can be taken as a summation node using some linearly independent families, such as, polynomial, exponential, Fourier, etc. The algorithm is demonstrated by two examples and compared with other common algorithms in both computer science and statistics communities.

KW - Dynamic programming

KW - Functional networks

KW - Interpolation

KW - Minimum description length

UR - http://www.scopus.com/inward/record.url?scp=84866520045&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84866520045

SN - 9781601320254

T3 - Proceedings of the 2007 International Conference on Artificial Intelligence, ICAI 2007

SP - 801

EP - 805

BT - Proceedings of the 2007 International Conference on Artificial Intelligence, ICAI 2007

ER -