Block training methods for perceptrons and their applications

No abstract is available for this paper.

• Publication year

  1997

• Venue

  Defense, Security, and Sensing

• Publication date

  1997-04-04

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1117/12.271522
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A comparative study of optimization techniques for backpropagation

  1994influential reference
• Minimisation methods for training feedforward neural networks

  1994cited by this paper
• A learning algorithm for multilayered neural networks based on linear least squares problems

  1993cited by this paper
• LS-based training algorithm for neural networks

  1993cited by this paper
• Neural network applications to nonlinear time series analysis

  1992cited by this paper
• Learning rate schedules for faster stochastic gradient search

  1992cited by this paper
• First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method

  1992cited by this paper
• A simple 'linearized' learning algorithm which outperforms back-propagation

  1992cited by this paper
• Fast learning algorithms for neural networks

  1992influential reference
• Benefits of gain: speeded learning and minimal hidden layers in back-propagation networks

  1991cited by this paper
• Linearized least-squares training of multilayer feedforward neural networks

  1991cited by this paper
• Learning with hidden targets

  1990cited by this paper
• Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights

  1990cited by this paper
• The "Moving Targets" Training Algorithm

  1989cited by this paper
• A generalization of the Eckart-Young-Mirsky matrix approximation theorem

  1987cited by this paper
• Increased rates of convergence through learning rate adaptation

  1987cited by this paper

• No citing papers are available for this paper.