Characteristics of Small Scale Non-Monotonic Neuron Networks Having Large Potentiality for Learning

IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4 p. 4171
Characteristics of Small Scale Non-Monotonic Neuron Networks Having Large Potentiality for Learning
Mitsunaga Kinjo, Tohoku University
Shigeo Sato, Tohoku University
Koji Nakajima, Tohoku University

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.860768
Send link to a friend

Abstract
In this paper, we report a study on learning ability of a Deterministic Boltzmann Machine (DBM) [1, 2] with neurons, which have a non-monotonic activation function. We use an end-cut-off-type function with a threshold parameter '?' as the non-monotonic function. Numerical simulations of nonlinear problems, such as the 2-Parity problem and the 4-Parity problem, show that the DBM network with non-monotonic neurons has higher learning ability compared to the network with monotonic neurons.
Back to Top Additional Information
Citation: Mitsunaga Kinjo, Shigeo Sato, Koji Nakajima, "Characteristics of Small Scale Non-Monotonic Neuron Networks Having Large Potentiality for Learning," ijcnn, p. 4171, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4, 2000

	Advanced Search
CS Search Google Search