Backpropagation (or backprop) algorithm is one of the well-known algorithms in neural networks. It is capable to deal with various types of data and also able to model a complex decision system. Some problem domains involve a large amount of data. The bigger the number of input or hidden units is, the more complex the model would be. Hence, reducing the network complexity would be an advantage ...

This paper proposes a version of the backpropagation algorithm which increases the tolerance of a feedforward neural network against deviations in the weight values. These changes can originate either when the neural network is mapped on a given VLSI circuit where the precision and/or weight matching are low, or by physical defects a!ecting the neural circuits. The modi"ed backpropagation algor...

Standard error backpropagation is used in almost all modern deep network training. However, it typically suffers from proliferation of saddle points in high-dimensional parameter space. Therefore, it is highly desirable to design an efficient algorithm to escape from these saddle points and reach a good parameter region of better generalization capabilities, especially based on rough insights a...

Neural networks can be classified into recurrent and nonrecurrent categories. Nonrecurrent (feedforward) networks have no feedback elements; the output is calculated directly from the input through feedforward connections. In recurrent networks the output depends not only on the current input to the network, but also on the current or previous outputs or states of the network. For this reason, ...

Unlike feedforward neural networks (FFNN) which can act as universal function approximaters, recursive neural networks have the potential to act as both universal function approximaters and universal system approximaters. In this paper, a globally recursive neural network least mean square (GRNNLMS) gradient descent or a real time recursive backpropagation (RTRBP) algorithm is developed for a s...