Information theoretic derivation of network architecture and learning algorithms
Conference
·
OSTI ID:5749333
Using variational techniques, we derive a feedforward network architecture that minimizes a least squares cost function with the soft constraint that the mutual information between input and output be maximized. This permits optimum generalization for a given accuracy. A set of learning algorithms are also obtained. The network and learning algorithms are tested on a set of test problems which emphasize time series prediction. 6 refs., 1 fig.
- Research Organization:
- Los Alamos National Lab., NM (USA)
- Sponsoring Organization:
- USDOE; USDOE, Washington, DC (USA)
- DOE Contract Number:
- W-7405-ENG-36
- OSTI ID:
- 5749333
- Report Number(s):
- LA-UR-91-325; CONF-910779-3; ON: DE91007552
- Resource Relation:
- Conference: 1991 international joint conference on neural networks (IJCNN), Seattle, WA (USA), 8-12 Jul 1991
- Country of Publication:
- United States
- Language:
- English
Similar Records
MABAL: a Novel Deep-Learning Architecture for Machine-Assisted Bone Age Labeling
Recursive least-squares learning algorithms for neural networks
Application of Genetic Algorithm in determining optimal backpropagation neural network architecture for ground-level ozone forecasting model
Journal Article
·
Wed Aug 15 00:00:00 EDT 2018
· Journal of Digital Imaging (Online)
·
OSTI ID:5749333
+1 more
Recursive least-squares learning algorithms for neural networks
Conference
·
Mon Jan 01 00:00:00 EST 1990
·
OSTI ID:5749333
Application of Genetic Algorithm in determining optimal backpropagation neural network architecture for ground-level ozone forecasting model
Conference
·
Thu Jul 01 00:00:00 EDT 1999
·
OSTI ID:5749333