Newton s method and the fastest descent in network optimization

The behavior of learnable systems is expressed by feedback algorithms, which are called learning rules. There are different types of learning rules for neural networks, and functional learning is one of them. In this type of learning, the parameters of the network are adjusted in such a way that the performance of the network is optimized. Optimizing network performance means minimizing the error that exists between the experimental values and the network response. In this article, in order to optimize network performance, we compare the two methods of fastest descent and Newton s method