Sciweavers

90 search results - page 8 / 18
» tnn 2008
Sort
View
TNN
1998
114views more  TNN 1998»
13 years 6 months ago
A new approach to artificial neural networks
: A novel approach to artificial neural networks is presented. The philosophy of this approach is based on two aspects: the design of task-specific networks, and a new neuron model...
Benedito Dias Baptista F. Filho, Eduardo Lobo Lust...
TNN
1998
112views more  TNN 1998»
13 years 6 months ago
A class of competitive learning models which avoids neuron underutilization problem
— In this paper, we study a qualitative property of a class of competitive learning (CL) models, which is called the multiplicatively biased competitive learning (MBCL) model, na...
Clifford Sze-Tsan Choy, Wan-Chi Siu
TNN
1998
76views more  TNN 1998»
13 years 6 months ago
Multiobjective genetic algorithm partitioning for hierarchical learning of high-dimensional pattern spaces: a learning-follows-d
— In this paper, we present a novel approach to partitioning pattern spaces using a multiobjective genetic algorithm for identifying (near-)optimal subspaces for hierarchical lea...
Rajeev Kumar, Peter Rockett
TNN
1998
100views more  TNN 1998»
13 years 6 months ago
A dynamical system perspective of structural learning with forgetting
—Structural learning with forgetting is an established method of using Laplace regularization to generate skeletal artificial neural networks. In this paper we develop a continu...
D. A. Miller, J. M. Zurada
TNN
2008
177views more  TNN 2008»
13 years 6 months ago
Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model
Previous work on statistical language modeling has shown that it is possible to train a feed-forward neural network to approximate probabilities over sequences of words, resulting...
Yoshua Bengio, Jean-Sébastien Senecal