Accelerated Backpropagation Learning : Parallel Tangent Optimization Algorithm

@inproceedings{Ghorbani1983AcceleratedBL,
  title={Accelerated Backpropagation Learning : Parallel Tangent Optimization Algorithm},
  author={Ali A. Ghorbani and Virendra Bhavsar},
  year={1983}
}
A modi ed backpropagation learning algorithm for training arti cial neural networks using de ecting gradient technique, which may be considered as a special case of the conjugate gradient methods, is proposed. Parallel tangent(Partan) gradient is used as an alternative for momentum term to accelerate the convergence. Partan gradient consists of two phases namely, climbing through gradient and accelerating through parallel tangent. Partan over- 

Similar Papers

Loading similar papers…