Accelerating backpropagation through dynamic self-adaptation

  title={Accelerating backpropagation through dynamic self-adaptation},
  author={Ralf Solomon and J. Leo van Hemmen},
  journal={Neural Networks},
Standard backpropagation and many procedures derived from it use the steepest-descent method to minimize a cost function. In this paper, we present a new genetic algorithm, dynamic self-adaptation, to accelerate steepest descent as it is used in iterative procedures. The underlying idea is to take the learning rate of the previous step, to increase and decrease it slightly, to evaluate the cost function for both new values of the learning rate, and to choose the one that gives the lower value… CONTINUE READING

From This Paper

Topics from this paper.
37 Citations
9 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 37 extracted citations

Similar Papers

Loading similar papers…