Analyzing weight distribution of feedforward neural networks and efficient weight initialization
From MaRDI portal
Recommendations
- An independent component analysis based weight initialization method for multilayer perceptrons
- New weight learning strategy for fully connected feedforward neural networks
- New Approach of Recurrent Neural Network Weight Initialization
- A weight initialization based on the linear product structure for neural networks
- Solving the linear interval tolerance problem for weight initialization of neural networks
Cited in
(13)- An independent component analysis based weight initialization method for multilayer perceptrons
- A new initialization method for neural networks with weight sharing
- A frequency-domain approach to improve ANNs generalization quality via proper initialization
- A weight initialization based on the linear product structure for neural networks
- Centred weight initialization in neural networks for object detection
- New weight learning strategy for fully connected feedforward neural networks
- Analysis of pre-training and initialization methods of neural networks
- Power function error initialization can improve convergence of backpropagation learning in neural networks for classification
- New Approach of Recurrent Neural Network Weight Initialization
- Efficient Initialization of Artificial Neural Network Weights for Electrical Component Models
- A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers
- Improved weight initialization for deep and narrow feedforward neural network
- Comparative analysis of the results of training a neural network with calculated weights and with random generation of the weights
This page was built for publication: Analyzing weight distribution of feedforward neural networks and efficient weight initialization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5466426)